diff --git a/README.md b/README.md
index 037bad8..e57edbf 100644
--- a/README.md
+++ b/README.md
@@ -75,28 +75,35 @@ Unlike openai-whisper, FFmpeg does **not** need to be installed on the system. T
 
 GPU execution requires the following NVIDIA libraries to be installed:
 
-* [cuBLAS for CUDA 11](https://developer.nvidia.com/cublas)
-* [cuDNN 8 for CUDA 11](https://developer.nvidia.com/cudnn)
+* [cuBLAS for CUDA 12](https://developer.nvidia.com/cublas)
+* [cuDNN 8 for CUDA 12](https://developer.nvidia.com/cudnn)
 
-There are multiple ways to install these libraries. The recommended way is described in the official NVIDIA documentation, but we also suggest other installation methods below.
+**Note**: Latest versions of `ctranslate2` support CUDA 12 only. For CUDA 11, the current workaround is downgrading to the `3.24.0` version of `ctranslate2` (This can be done with `pip install --force-reinstall ctranslate2==3.24.0` or specifying the version in a `requirements.txt`).
+
+There are multiple ways to install the NVIDIA libraries mentioned above. The recommended way is described in the official NVIDIA documentation, but we also suggest other installation methods below. 
 
 <details>
 <summary>Other installation methods (click to expand)</summary>
 
+
+**Note:** For all these methods below, keep in mind the above note regarding CUDA versions. Depending on your setup, you may need to install the _CUDA 11_ versions of libraries that correspond to the CUDA 12 libraries listed in the instructions below.
+
 #### Use Docker
 
-The libraries are installed in this official NVIDIA Docker image: `nvidia/cuda:11.8.0-cudnn8-runtime-ubuntu22.04`.
+The libraries (cuBLAS, cuDNN) are installed in these official NVIDIA CUDA Docker images: `nvidia/cuda:12.0.0-runtime-ubuntu20.04` or `nvidia/cuda:12.0.0-runtime-ubuntu22.04`.
 
 #### Install with `pip` (Linux only)
 
 On Linux these libraries can be installed with `pip`. Note that `LD_LIBRARY_PATH` must be set before launching Python.
 
 ```bash
-pip install nvidia-cublas-cu11 nvidia-cudnn-cu11
+pip install nvidia-cublas-cu12 nvidia-cudnn-cu12
 
 export LD_LIBRARY_PATH=`python3 -c 'import os; import nvidia.cublas.lib; import nvidia.cudnn.lib; print(os.path.dirname(nvidia.cublas.lib.__file__) + ":" + os.path.dirname(nvidia.cudnn.lib.__file__))'`
 ```
 
+**Note**: Version 9+ of `nvidia-cudnn-cu12` appears to cause issues due its reliance on cuDNN 9 (Faster-Whisper does not currently support cuDNN 9). Ensure your version of the Python package is for cuDNN 8.
+
 #### Download the libraries from Purfview's repository (Windows & Linux)
 
 Purfview's [whisper-standalone-win](https://github.com/Purfview/whisper-standalone-win) provides the required NVIDIA libraries for Windows & Linux in a [single archive](https://github.com/Purfview/whisper-standalone-win/releases/tag/libs). Decompress the archive and place the libraries in a directory included in the `PATH`.
@@ -227,6 +234,7 @@ See more model and transcription options in the [`WhisperModel`](https://github.
 Here is a non exhaustive list of open-source projects using faster-whisper. Feel free to add your project to the list!
 
 
+* [faster-whisper-server](https://github.com/fedirz/faster-whisper-server) is an OpenAI compatible server using `faster-whisper`. It's easily deployable with Docker, works with OpenAI SDKs/CLI, supports streaming, and live transcription.
 * [WhisperX](https://github.com/m-bain/whisperX) is an award-winning Python library that offers speaker diarization and accurate word-level timestamps using wav2vec2 alignment
 * [whisper-ctranslate2](https://github.com/Softcatala/whisper-ctranslate2) is a command line client based on faster-whisper and compatible with the original client from openai/whisper.
 * [whisper-diarize](https://github.com/MahmoudAshraf97/whisper-diarization) is a speaker diarization tool that is based on faster-whisper and NVIDIA NeMo.
diff --git a/benchmark/benchmark.m4a b/benchmark/benchmark.m4a
new file mode 100644
index 0000000..66259d7
Binary files /dev/null and b/benchmark/benchmark.m4a differ
diff --git a/benchmark/memory_benchmark.py b/benchmark/memory_benchmark.py
new file mode 100644
index 0000000..1fbdfbd
--- /dev/null
+++ b/benchmark/memory_benchmark.py
@@ -0,0 +1,94 @@
+import argparse
+import time
+
+from typing import Callable
+
+import py3nvml.py3nvml as nvml
+
+from memory_profiler import memory_usage
+from utils import MyThread, get_logger, inference
+
+logger = get_logger("faster-whisper")
+parser = argparse.ArgumentParser(description="Memory benchmark")
+parser.add_argument(
+    "--gpu_memory", action="store_true", help="Measure GPU memory usage"
+)
+parser.add_argument("--device-index", type=int, default=0, help="GPU device index")
+parser.add_argument(
+    "--interval",
+    type=float,
+    default=0.5,
+    help="Interval at which measurements are collected",
+)
+args = parser.parse_args()
+device_idx = args.device_index
+interval = args.interval
+
+
+def measure_memory(func: Callable[[], None]):
+    if args.gpu_memory:
+        logger.info(
+            "Measuring maximum GPU memory usage on GPU device."
+            " Make sure to not have additional processes running on the same GPU."
+        )
+        # init nvml
+        nvml.nvmlInit()
+        handle = nvml.nvmlDeviceGetHandleByIndex(device_idx)
+        gpu_name = nvml.nvmlDeviceGetName(handle)
+        gpu_memory_limit = nvml.nvmlDeviceGetMemoryInfo(handle).total >> 20
+        gpu_power_limit = nvml.nvmlDeviceGetPowerManagementLimit(handle) / 1000.0
+        info = {"gpu_memory_usage": [], "gpu_power_usage": []}
+
+        def _get_gpu_info():
+            while True:
+                info["gpu_memory_usage"].append(
+                    nvml.nvmlDeviceGetMemoryInfo(handle).used >> 20
+                )
+                info["gpu_power_usage"].append(
+                    nvml.nvmlDeviceGetPowerUsage(handle) / 1000
+                )
+                time.sleep(interval)
+
+                if stop:
+                    break
+
+            return info
+
+        stop = False
+        thread = MyThread(_get_gpu_info, params=())
+        thread.start()
+        func()
+        stop = True
+        thread.join()
+        result = thread.get_result()
+
+        # shutdown nvml
+        nvml.nvmlShutdown()
+        max_memory_usage = max(result["gpu_memory_usage"])
+        max_power_usage = max(result["gpu_power_usage"])
+        print("GPU name: %s" % gpu_name)
+        print("GPU device index: %s" % device_idx)
+        print(
+            "Maximum GPU memory usage: %dMiB / %dMiB (%.2f%%)"
+            % (
+                max_memory_usage,
+                gpu_memory_limit,
+                (max_memory_usage / gpu_memory_limit) * 100,
+            )
+        )
+        print(
+            "Maximum GPU power usage: %dW / %dW (%.2f%%)"
+            % (
+                max_power_usage,
+                gpu_power_limit,
+                (max_power_usage / gpu_power_limit) * 100,
+            )
+        )
+    else:
+        logger.info("Measuring maximum increase of memory usage.")
+        max_usage = memory_usage(func, max_usage=True, interval=interval)
+        print("Maximum increase of RAM memory usage: %d MiB" % max_usage)
+
+
+if __name__ == "__main__":
+    measure_memory(inference)
diff --git a/benchmark/normalizer.json b/benchmark/normalizer.json
new file mode 100644
index 0000000..dd6ae81
--- /dev/null
+++ b/benchmark/normalizer.json
@@ -0,0 +1,1742 @@
+{
+  "accessorise": "accessorize",
+  "accessorised": "accessorized",
+  "accessorises": "accessorizes",
+  "accessorising": "accessorizing",
+  "acclimatisation": "acclimatization",
+  "acclimatise": "acclimatize",
+  "acclimatised": "acclimatized",
+  "acclimatises": "acclimatizes",
+  "acclimatising": "acclimatizing",
+  "accoutrements": "accouterments",
+  "aeon": "eon",
+  "aeons": "eons",
+  "aerogramme": "aerogram",
+  "aerogrammes": "aerograms",
+  "aeroplane": "airplane",
+  "aeroplanes": "airplanes",
+  "aesthete": "esthete",
+  "aesthetes": "esthetes",
+  "aesthetic": "esthetic",
+  "aesthetically": "esthetically",
+  "aesthetics": "esthetics",
+  "aetiology": "etiology",
+  "ageing": "aging",
+  "aggrandisement": "aggrandizement",
+  "agonise": "agonize",
+  "agonised": "agonized",
+  "agonises": "agonizes",
+  "agonising": "agonizing",
+  "agonisingly": "agonizingly",
+  "almanack": "almanac",
+  "almanacks": "almanacs",
+  "aluminium": "aluminum",
+  "amortisable": "amortizable",
+  "amortisation": "amortization",
+  "amortisations": "amortizations",
+  "amortise": "amortize",
+  "amortised": "amortized",
+  "amortises": "amortizes",
+  "amortising": "amortizing",
+  "amphitheatre": "amphitheater",
+  "amphitheatres": "amphitheaters",
+  "anaemia": "anemia",
+  "anaemic": "anemic",
+  "anaesthesia": "anesthesia",
+  "anaesthetic": "anesthetic",
+  "anaesthetics": "anesthetics",
+  "anaesthetise": "anesthetize",
+  "anaesthetised": "anesthetized",
+  "anaesthetises": "anesthetizes",
+  "anaesthetising": "anesthetizing",
+  "anaesthetist": "anesthetist",
+  "anaesthetists": "anesthetists",
+  "anaesthetize": "anesthetize",
+  "anaesthetized": "anesthetized",
+  "anaesthetizes": "anesthetizes",
+  "anaesthetizing": "anesthetizing",
+  "analogue": "analog",
+  "analogues": "analogs",
+  "analyse": "analyze",
+  "analysed": "analyzed",
+  "analyses": "analyzes",
+  "analysing": "analyzing",
+  "anglicise": "anglicize",
+  "anglicised": "anglicized",
+  "anglicises": "anglicizes",
+  "anglicising": "anglicizing",
+  "annualised": "annualized",
+  "antagonise": "antagonize",
+  "antagonised": "antagonized",
+  "antagonises": "antagonizes",
+  "antagonising": "antagonizing",
+  "apologise": "apologize",
+  "apologised": "apologized",
+  "apologises": "apologizes",
+  "apologising": "apologizing",
+  "appal": "appall",
+  "appals": "appalls",
+  "appetiser": "appetizer",
+  "appetisers": "appetizers",
+  "appetising": "appetizing",
+  "appetisingly": "appetizingly",
+  "arbour": "arbor",
+  "arbours": "arbors",
+  "archaeologically": "archeologically",
+  "archaeologist": "archeologist",
+  "archaeologists": "archeologists",
+  "archaeology": "archeology</span>",
+  "archeological": "archaeological",
+  "ardour": "ardor",
+  "armour": "armor",
+  "armoured": "armored",
+  "armourer": "armorer",
+  "armourers": "armorers",
+  "armouries": "armories",
+  "armoury": "armory",
+  "artefact": "artifact",
+  "artefacts": "artifacts",
+  "authorise": "authorize",
+  "authorised": "authorized",
+  "authorises": "authorizes",
+  "authorising": "authorizing",
+  "axe": "ax",
+  "backpedalled": "backpedaled",
+  "backpedalling": "backpedaling",
+  "bannister": "banister",
+  "bannisters": "banisters",
+  "baptise": "baptize",
+  "baptised": "baptized",
+  "baptises": "baptizes",
+  "baptising": "baptizing",
+  "bastardise": "bastardize",
+  "bastardised": "bastardized",
+  "bastardises": "bastardizes",
+  "bastardising": "bastardizing",
+  "battleax": "battleaxe",
+  "baulk": "balk",
+  "baulked": "balked",
+  "baulking": "balking",
+  "baulks": "balks",
+  "bedevilled": "bedeviled",
+  "bedevilling": "bedeviling",
+  "behaviour": "behavior",
+  "behavioural": "behavioral",
+  "behaviourism": "behaviorism",
+  "behaviourist": "behaviorist",
+  "behaviourists": "behaviorists",
+  "behaviours": "behaviors",
+  "behove": "behoove",
+  "behoved": "behooved",
+  "behoves": "behooves",
+  "bejewelled": "bejeweled",
+  "belabour": "belabor",
+  "belaboured": "belabored",
+  "belabouring": "belaboring",
+  "belabours": "belabors",
+  "bevelled": "beveled",
+  "bevvies": "bevies",
+  "bevvy": "bevy",
+  "biassed": "biased",
+  "biassing": "biasing",
+  "bingeing": "binging",
+  "bougainvillaea": "bougainvillea",
+  "bougainvillaeas": "bougainvilleas",
+  "bowdlerise": "bowdlerize",
+  "bowdlerised": "bowdlerized",
+  "bowdlerises": "bowdlerizes",
+  "bowdlerising": "bowdlerizing",
+  "breathalyse": "breathalyze",
+  "breathalysed": "breathalyzed",
+  "breathalyser": "breathalyzer",
+  "breathalysers": "breathalyzers",
+  "breathalyses": "breathalyzes",
+  "breathalysing": "breathalyzing",
+  "brutalise": "brutalize",
+  "brutalised": "brutalized",
+  "brutalises": "brutalizes",
+  "brutalising": "brutalizing",
+  "busses": "buses",
+  "bussing": "busing",
+  "caesarean": "cesarean",
+  "caesareans": "cesareans",
+  "calibre": "caliber",
+  "calibres": "calibers",
+  "calliper": "caliper",
+  "callipers": "calipers",
+  "callisthenics": "calisthenics",
+  "canalise": "canalize",
+  "canalised": "canalized",
+  "canalises": "canalizes",
+  "canalising": "canalizing",
+  "cancelation": "cancellation",
+  "cancelations": "cancellations",
+  "cancelled": "canceled",
+  "cancelling": "canceling",
+  "candour": "candor",
+  "cannibalise": "cannibalize",
+  "cannibalised": "cannibalized",
+  "cannibalises": "cannibalizes",
+  "cannibalising": "cannibalizing",
+  "canonise": "canonize",
+  "canonised": "canonized",
+  "canonises": "canonizes",
+  "canonising": "canonizing",
+  "capitalise": "capitalize",
+  "capitalised": "capitalized",
+  "capitalises": "capitalizes",
+  "capitalising": "capitalizing",
+  "caramelise": "caramelize",
+  "caramelised": "caramelized",
+  "caramelises": "caramelizes",
+  "caramelising": "caramelizing",
+  "carbonise": "carbonize",
+  "carbonised": "carbonized",
+  "carbonises": "carbonizes",
+  "carbonising": "carbonizing",
+  "carolled": "caroled",
+  "carolling": "caroling",
+  "catalogue": "catalog",
+  "catalogued": "cataloged",
+  "catalogues": "catalogs",
+  "cataloguing": "cataloging",
+  "catalyse": "catalyze",
+  "catalysed": "catalyzed",
+  "catalyses": "catalyzes",
+  "catalysing": "catalyzing",
+  "categorise": "categorize",
+  "categorised": "categorized",
+  "categorises": "categorizes",
+  "categorising": "categorizing",
+  "cauterise": "cauterize",
+  "cauterised": "cauterized",
+  "cauterises": "cauterizes",
+  "cauterising": "cauterizing",
+  "cavilled": "caviled",
+  "cavilling": "caviling",
+  "centigramme": "centigram",
+  "centigrammes": "centigrams",
+  "centilitre": "centiliter",
+  "centilitres": "centiliters",
+  "centimetre": "centimeter",
+  "centimetres": "centimeters",
+  "centralise": "centralize",
+  "centralised": "centralized",
+  "centralises": "centralizes",
+  "centralising": "centralizing",
+  "centre": "center",
+  "centred": "centered",
+  "centrefold": "centerfold",
+  "centrefolds": "centerfolds",
+  "centrepiece": "centerpiece",
+  "centrepieces": "centerpieces",
+  "centres": "centers",
+  "channelled": "channeled",
+  "channelling": "channeling",
+  "characterise": "characterize",
+  "characterised": "characterized",
+  "characterises": "characterizes",
+  "characterising": "characterizing",
+  "cheque": "check",
+  "chequebook": "checkbook",
+  "chequebooks": "checkbooks",
+  "chequered": "checkered",
+  "cheques": "checks",
+  "chilli": "chili",
+  "chimaera": "chimera",
+  "chimaeras": "chimeras",
+  "chiselled": "chiseled",
+  "chiselling": "chiseling",
+  "circularise": "circularize",
+  "circularised": "circularized",
+  "circularises": "circularizes",
+  "circularising": "circularizing",
+  "civilise": "civilize",
+  "civilised": "civilized",
+  "civilises": "civilizes",
+  "civilising": "civilizing",
+  "clamour": "clamor",
+  "clamoured": "clamored",
+  "clamouring": "clamoring",
+  "clamours": "clamors",
+  "clangour": "clangor",
+  "clarinettist": "clarinetist",
+  "clarinettists": "clarinetists",
+  "collectivise": "collectivize",
+  "collectivised": "collectivized",
+  "collectivises": "collectivizes",
+  "collectivising": "collectivizing",
+  "colonisation": "colonization",
+  "colonise": "colonize",
+  "colonised": "colonized",
+  "coloniser": "colonizer",
+  "colonisers": "colonizers",
+  "colonises": "colonizes",
+  "colonising": "colonizing",
+  "colour": "color",
+  "colourant": "colorant",
+  "colourants": "colorants",
+  "coloured": "colored",
+  "coloureds": "coloreds",
+  "colourful": "colorful",
+  "colourfully": "colorfully",
+  "colouring": "coloring",
+  "colourize": "colorize",
+  "colourized": "colorized",
+  "colourizes": "colorizes",
+  "colourizing": "colorizing",
+  "colourless": "colorless",
+  "colours": "colors",
+  "commercialise": "commercialize",
+  "commercialised": "commercialized",
+  "commercialises": "commercializes",
+  "commercialising": "commercializing",
+  "compartmentalise": "compartmentalize",
+  "compartmentalised": "compartmentalized",
+  "compartmentalises": "compartmentalizes",
+  "compartmentalising": "compartmentalizing",
+  "computerise": "computerize",
+  "computerised": "computerized",
+  "computerises": "computerizes",
+  "computerising": "computerizing",
+  "conceptualise": "conceptualize",
+  "conceptualised": "conceptualized",
+  "conceptualises": "conceptualizes",
+  "conceptualising": "conceptualizing",
+  "connexion": "connection",
+  "connexions": "connections",
+  "contextualise": "contextualize",
+  "contextualised": "contextualized",
+  "contextualises": "contextualizes",
+  "contextualising": "contextualizing",
+  "cosier": "cozier",
+  "cosies": "cozies",
+  "cosiest": "coziest",
+  "cosily": "cozily",
+  "cosiness": "coziness",
+  "cosy": "cozy",
+  "councillor": "councilor",
+  "councillors": "councilors",
+  "counselled": "counseled",
+  "counselling": "counseling",
+  "counsellor": "counselor",
+  "counsellors": "counselors",
+  "crenelated": "crenellated",
+  "criminalise": "criminalize",
+  "criminalised": "criminalized",
+  "criminalises": "criminalizes",
+  "criminalising": "criminalizing",
+  "criticise": "criticize",
+  "criticised": "criticized",
+  "criticises": "criticizes",
+  "criticising": "criticizing",
+  "crueller": "crueler",
+  "cruellest": "cruelest",
+  "crystallisation": "crystallization",
+  "crystallise": "crystallize",
+  "crystallised": "crystallized",
+  "crystallises": "crystallizes",
+  "crystallising": "crystallizing",
+  "cudgelled": "cudgeled",
+  "cudgelling": "cudgeling",
+  "customise": "customize",
+  "customised": "customized",
+  "customises": "customizes",
+  "customising": "customizing",
+  "cypher": "cipher",
+  "cyphers": "ciphers",
+  "decentralisation": "decentralization",
+  "decentralise": "decentralize",
+  "decentralised": "decentralized",
+  "decentralises": "decentralizes",
+  "decentralising": "decentralizing",
+  "decriminalisation": "decriminalization",
+  "decriminalise": "decriminalize",
+  "decriminalised": "decriminalized",
+  "decriminalises": "decriminalizes",
+  "decriminalising": "decriminalizing",
+  "defence": "defense",
+  "defenceless": "defenseless",
+  "defences": "defenses",
+  "dehumanisation": "dehumanization",
+  "dehumanise": "dehumanize",
+  "dehumanised": "dehumanized",
+  "dehumanises": "dehumanizes",
+  "dehumanising": "dehumanizing",
+  "demeanour": "demeanor",
+  "demilitarisation": "demilitarization",
+  "demilitarise": "demilitarize",
+  "demilitarised": "demilitarized",
+  "demilitarises": "demilitarizes",
+  "demilitarising": "demilitarizing",
+  "demobilisation": "demobilization",
+  "demobilise": "demobilize",
+  "demobilised": "demobilized",
+  "demobilises": "demobilizes",
+  "demobilising": "demobilizing",
+  "democratisation": "democratization",
+  "democratise": "democratize",
+  "democratised": "democratized",
+  "democratises": "democratizes",
+  "democratising": "democratizing",
+  "demonise": "demonize",
+  "demonised": "demonized",
+  "demonises": "demonizes",
+  "demonising": "demonizing",
+  "demoralisation": "demoralization",
+  "demoralise": "demoralize",
+  "demoralised": "demoralized",
+  "demoralises": "demoralizes",
+  "demoralising": "demoralizing",
+  "denationalisation": "denationalization",
+  "denationalise": "denationalize",
+  "denationalised": "denationalized",
+  "denationalises": "denationalizes",
+  "denationalising": "denationalizing",
+  "deodorise": "deodorize",
+  "deodorised": "deodorized",
+  "deodorises": "deodorizes",
+  "deodorising": "deodorizing",
+  "depersonalise": "depersonalize",
+  "depersonalised": "depersonalized",
+  "depersonalises": "depersonalizes",
+  "depersonalising": "depersonalizing",
+  "deputise": "deputize",
+  "deputised": "deputized",
+  "deputises": "deputizes",
+  "deputising": "deputizing",
+  "desensitisation": "desensitization",
+  "desensitise": "desensitize",
+  "desensitised": "desensitized",
+  "desensitises": "desensitizes",
+  "desensitising": "desensitizing",
+  "destabilisation": "destabilization",
+  "destabilise": "destabilize",
+  "destabilised": "destabilized",
+  "destabilises": "destabilizes",
+  "destabilising": "destabilizing",
+  "dialled": "dialed",
+  "dialling": "dialing",
+  "dialogue": "dialog",
+  "dialogues": "dialogs",
+  "diarrhoea": "diarrhea",
+  "digitise": "digitize",
+  "digitised": "digitized",
+  "digitises": "digitizes",
+  "digitising": "digitizing",
+  "disc": "disk",
+  "discolour": "discolor",
+  "discoloured": "discolored",
+  "discolouring": "discoloring",
+  "discolours": "discolors",
+  "discs": "disks",
+  "disembowelled": "disemboweled",
+  "disembowelling": "disemboweling",
+  "disfavour": "disfavor",
+  "dishevelled": "disheveled",
+  "dishonour": "dishonor",
+  "dishonourable": "dishonorable",
+  "dishonourably": "dishonorably",
+  "dishonoured": "dishonored",
+  "dishonouring": "dishonoring",
+  "dishonours": "dishonors",
+  "disorganisation": "disorganization",
+  "disorganised": "disorganized",
+  "distil": "distill",
+  "distils": "distills",
+  "dramatisation": "dramatization",
+  "dramatisations": "dramatizations",
+  "dramatise": "dramatize",
+  "dramatised": "dramatized",
+  "dramatises": "dramatizes",
+  "dramatising": "dramatizing",
+  "draught": "draft",
+  "draughtboard": "draftboard",
+  "draughtboards": "draftboards",
+  "draughtier": "draftier",
+  "draughtiest": "draftiest",
+  "draughts": "drafts",
+  "draughtsman": "draftsman",
+  "draughtsmanship": "draftsmanship",
+  "draughtsmen": "draftsmen",
+  "draughtswoman": "draftswoman",
+  "draughtswomen": "draftswomen",
+  "draughty": "drafty",
+  "drivelled": "driveled",
+  "drivelling": "driveling",
+  "duelled": "dueled",
+  "duelling": "dueling",
+  "economise": "economize",
+  "economised": "economized",
+  "economises": "economizes",
+  "economising": "economizing",
+  "editorialise": "editorialize",
+  "editorialised": "editorialized",
+  "editorialises": "editorializes",
+  "editorialising": "editorializing",
+  "edoema": "edema",
+  "empathise": "empathize",
+  "empathised": "empathized",
+  "empathises": "empathizes",
+  "empathising": "empathizing",
+  "emphasise": "emphasize",
+  "emphasised": "emphasized",
+  "emphasises": "emphasizes",
+  "emphasising": "emphasizing",
+  "enamelled": "enameled",
+  "enamelling": "enameling",
+  "enamoured": "enamored",
+  "encyclopaedia": "encyclopedia",
+  "encyclopaedias": "encyclopedias",
+  "encyclopaedic": "encyclopedic",
+  "endeavour": "endeavor",
+  "endeavoured": "endeavored",
+  "endeavouring": "endeavoring",
+  "endeavours": "endeavors",
+  "energise": "energize",
+  "energised": "energized",
+  "energises": "energizes",
+  "energising": "energizing",
+  "enrol": "enroll",
+  "enrols": "enrolls",
+  "enthral": "enthrall",
+  "enthrals": "enthralls",
+  "epaulette": "epaulet",
+  "epaulettes": "epaulets",
+  "epicentre": "epicenter",
+  "epicentres": "epicenters",
+  "epilogue": "epilog",
+  "epilogues": "epilogs",
+  "epitomise": "epitomize",
+  "epitomised": "epitomized",
+  "epitomises": "epitomizes",
+  "epitomising": "epitomizing",
+  "equalisation": "equalization",
+  "equalise": "equalize",
+  "equalised": "equalized",
+  "equaliser": "equalizer",
+  "equalisers": "equalizers",
+  "equalises": "equalizes",
+  "equalising": "equalizing",
+  "eulogise": "eulogize",
+  "eulogised": "eulogized",
+  "eulogises": "eulogizes",
+  "eulogising": "eulogizing",
+  "evangelise": "evangelize",
+  "evangelised": "evangelized",
+  "evangelises": "evangelizes",
+  "evangelising": "evangelizing",
+  "exorcise": "exorcize",
+  "exorcised": "exorcized",
+  "exorcises": "exorcizes",
+  "exorcising": "exorcizing",
+  "extemporisation": "extemporization",
+  "extemporise": "extemporize",
+  "extemporised": "extemporized",
+  "extemporises": "extemporizes",
+  "extemporising": "extemporizing",
+  "externalisation": "externalization",
+  "externalisations": "externalizations",
+  "externalise": "externalize",
+  "externalised": "externalized",
+  "externalises": "externalizes",
+  "externalising": "externalizing",
+  "factorise": "factorize",
+  "factorised": "factorized",
+  "factorises": "factorizes",
+  "factorising": "factorizing",
+  "faecal": "fecal",
+  "faeces": "feces",
+  "familiarisation": "familiarization",
+  "familiarise": "familiarize",
+  "familiarised": "familiarized",
+  "familiarises": "familiarizes",
+  "familiarising": "familiarizing",
+  "fantasise": "fantasize",
+  "fantasised": "fantasized",
+  "fantasises": "fantasizes",
+  "fantasising": "fantasizing",
+  "favour": "favor",
+  "favourable": "favorable",
+  "favourably": "favorably",
+  "favoured": "favored",
+  "favouring": "favoring",
+  "favourite": "favorite",
+  "favourites": "favorites",
+  "favouritism": "favoritism",
+  "favours": "favors",
+  "feminise": "feminize",
+  "feminised": "feminized",
+  "feminises": "feminizes",
+  "feminising": "feminizing",
+  "fertilisation": "fertilization",
+  "fertilise": "fertilize",
+  "fertilised": "fertilized",
+  "fertiliser": "fertilizer",
+  "fertilisers": "fertilizers",
+  "fertilises": "fertilizes",
+  "fertilising": "fertilizing",
+  "fervour": "fervor",
+  "fibre": "fiber",
+  "fibreglass": "fiberglass",
+  "fibres": "fibers",
+  "fictionalisation": "fictionalization",
+  "fictionalisations": "fictionalizations",
+  "fictionalise": "fictionalize",
+  "fictionalised": "fictionalized",
+  "fictionalises": "fictionalizes",
+  "fictionalising": "fictionalizing",
+  "fillet": "filet",
+  "filleted": "fileted",
+  "filleting": "fileting",
+  "fillets": "filets",
+  "finalisation": "finalization",
+  "finalise": "finalize",
+  "finalised": "finalized",
+  "finalises": "finalizes",
+  "finalising": "finalizing",
+  "flautist": "flutist",
+  "flautists": "flutists",
+  "flavour": "flavor",
+  "flavoured": "flavored",
+  "flavouring": "flavoring",
+  "flavourings": "flavorings",
+  "flavourless": "flavorless",
+  "flavours": "flavors",
+  "flavoursome": "flavorsome",
+  "flyer / flier": "flier / flyer",
+  "foetal": "fetal",
+  "foetid": "fetid",
+  "foetus": "fetus",
+  "foetuses": "fetuses",
+  "formalisation": "formalization",
+  "formalise": "formalize",
+  "formalised": "formalized",
+  "formalises": "formalizes",
+  "formalising": "formalizing",
+  "fossilisation": "fossilization",
+  "fossilise": "fossilize",
+  "fossilised": "fossilized",
+  "fossilises": "fossilizes",
+  "fossilising": "fossilizing",
+  "fraternisation": "fraternization",
+  "fraternise": "fraternize",
+  "fraternised": "fraternized",
+  "fraternises": "fraternizes",
+  "fraternising": "fraternizing",
+  "fulfil": "fulfill",
+  "fulfilment": "fulfillment",
+  "fulfils": "fulfills",
+  "funnelled": "funneled",
+  "funnelling": "funneling",
+  "gage": "gauge",
+  "gaged": "gauged",
+  "gages": "gauges",
+  "gaging": "gauging",
+  "galvanise": "galvanize",
+  "galvanised": "galvanized",
+  "galvanises": "galvanizes",
+  "galvanising": "galvanizing",
+  "gambolled": "gamboled",
+  "gambolling": "gamboling",
+  "gaol": "jail",
+  "gaolbird": "jailbird",
+  "gaolbirds": "jailbirds",
+  "gaolbreak": "jailbreak",
+  "gaolbreaks": "jailbreaks",
+  "gaoled": "jailed",
+  "gaoler": "jailer",
+  "gaolers": "jailers",
+  "gaoling": "jailing",
+  "gaols": "jails",
+  "gasses": "gases",
+  "generalisation": "generalization",
+  "generalisations": "generalizations",
+  "generalise": "generalize",
+  "generalised": "generalized",
+  "generalises": "generalizes",
+  "generalising": "generalizing",
+  "ghettoise": "ghettoize",
+  "ghettoised": "ghettoized",
+  "ghettoises": "ghettoizes",
+  "ghettoising": "ghettoizing",
+  "gipsies": "gypsies",
+  "glamor": "glamour",
+  "glamorise": "glamorize",
+  "glamorised": "glamorized",
+  "glamorises": "glamorizes",
+  "glamorising": "glamorizing",
+  "globalisation": "globalization",
+  "globalise": "globalize",
+  "globalised": "globalized",
+  "globalises": "globalizes",
+  "globalising": "globalizing",
+  "glueing": "gluing",
+  "goitre": "goiter",
+  "goitres": "goiters",
+  "gonorrhoea": "gonorrhea",
+  "gramme": "gram",
+  "grammes": "grams",
+  "gravelled": "graveled",
+  "grey": "gray",
+  "greyed": "grayed",
+  "greying": "graying",
+  "greyish": "grayish",
+  "greyness": "grayness",
+  "greys": "grays",
+  "grovelled": "groveled",
+  "grovelling": "groveling",
+  "groyne": "groin",
+  "groynes": "groins",
+  "gruelling": "grueling",
+  "gruellingly": "gruelingly",
+  "gryphon": "griffin",
+  "gryphons": "griffins",
+  "gynaecological": "gynecological",
+  "gynaecologist": "gynecologist",
+  "gynaecologists": "gynecologists",
+  "gynaecology": "gynecology",
+  "haematological": "hematological",
+  "haematologist": "hematologist",
+  "haematologists": "hematologists",
+  "haematology": "hematology",
+  "haemoglobin": "hemoglobin",
+  "haemophilia": "hemophilia",
+  "haemophiliac": "hemophiliac",
+  "haemophiliacs": "hemophiliacs",
+  "haemorrhage": "hemorrhage",
+  "haemorrhaged": "hemorrhaged",
+  "haemorrhages": "hemorrhages",
+  "haemorrhaging": "hemorrhaging",
+  "haemorrhoids": "hemorrhoids",
+  "harbour": "harbor",
+  "harboured": "harbored",
+  "harbouring": "harboring",
+  "harbours": "harbors",
+  "harmonisation": "harmonization",
+  "harmonise": "harmonize",
+  "harmonised": "harmonized",
+  "harmonises": "harmonizes",
+  "harmonising": "harmonizing",
+  "homoeopath": "homeopath",
+  "homoeopathic": "homeopathic",
+  "homoeopaths": "homeopaths",
+  "homoeopathy": "homeopathy",
+  "homogenise": "homogenize",
+  "homogenised": "homogenized",
+  "homogenises": "homogenizes",
+  "homogenising": "homogenizing",
+  "honour": "honor",
+  "honourable": "honorable",
+  "honourably": "honorably",
+  "honoured": "honored",
+  "honouring": "honoring",
+  "honours": "honors",
+  "hospitalisation": "hospitalization",
+  "hospitalise": "hospitalize",
+  "hospitalised": "hospitalized",
+  "hospitalises": "hospitalizes",
+  "hospitalising": "hospitalizing",
+  "humanise": "humanize",
+  "humanised": "humanized",
+  "humanises": "humanizes",
+  "humanising": "humanizing",
+  "humour": "humor",
+  "humoured": "humored",
+  "humouring": "humoring",
+  "humourless": "humorless",
+  "humours": "humors",
+  "hybridise": "hybridize",
+  "hybridised": "hybridized",
+  "hybridises": "hybridizes",
+  "hybridising": "hybridizing",
+  "hypnotise": "hypnotize",
+  "hypnotised": "hypnotized",
+  "hypnotises": "hypnotizes",
+  "hypnotising": "hypnotizing",
+  "hypothesise": "hypothesize",
+  "hypothesised": "hypothesized",
+  "hypothesises": "hypothesizes",
+  "hypothesising": "hypothesizing",
+  "idealisation": "idealization",
+  "idealise": "idealize",
+  "idealised": "idealized",
+  "idealises": "idealizes",
+  "idealising": "idealizing",
+  "idolise": "idolize",
+  "idolised": "idolized",
+  "idolises": "idolizes",
+  "idolising": "idolizing",
+  "immobilisation": "immobilization",
+  "immobilise": "immobilize",
+  "immobilised": "immobilized",
+  "immobiliser": "immobilizer",
+  "immobilisers": "immobilizers",
+  "immobilises": "immobilizes",
+  "immobilising": "immobilizing",
+  "immortalise": "immortalize",
+  "immortalised": "immortalized",
+  "immortalises": "immortalizes",
+  "immortalising": "immortalizing",
+  "immunisation": "immunization",
+  "immunise": "immunize",
+  "immunised": "immunized",
+  "immunises": "immunizes",
+  "immunising": "immunizing",
+  "impanelled": "impaneled",
+  "impanelling": "impaneling",
+  "imperilled": "imperiled",
+  "imperilling": "imperiling",
+  "individualise": "individualize",
+  "individualised": "individualized",
+  "individualises": "individualizes",
+  "individualising": "individualizing",
+  "industrialise": "industrialize",
+  "industrialised": "industrialized",
+  "industrialises": "industrializes",
+  "industrialising": "industrializing",
+  "inflexion": "inflection",
+  "inflexions": "inflections",
+  "initialise": "initialize",
+  "initialised": "initialized",
+  "initialises": "initializes",
+  "initialising": "initializing",
+  "initialled": "initialed",
+  "initialling": "initialing",
+  "instal": "install",
+  "instalment": "installment",
+  "instalments": "installments",
+  "instals": "installs",
+  "instil": "instill",
+  "instils": "instills",
+  "institutionalisation": "institutionalization",
+  "institutionalise": "institutionalize",
+  "institutionalised": "institutionalized",
+  "institutionalises": "institutionalizes",
+  "institutionalising": "institutionalizing",
+  "intellectualise": "intellectualize",
+  "intellectualised": "intellectualized",
+  "intellectualises": "intellectualizes",
+  "intellectualising": "intellectualizing",
+  "internalisation": "internalization",
+  "internalise": "internalize",
+  "internalised": "internalized",
+  "internalises": "internalizes",
+  "internalising": "internalizing",
+  "internationalisation": "internationalization",
+  "internationalise": "internationalize",
+  "internationalised": "internationalized",
+  "internationalises": "internationalizes",
+  "internationalising": "internationalizing",
+  "ionisation": "ionization",
+  "ionise": "ionize",
+  "ionised": "ionized",
+  "ioniser": "ionizer",
+  "ionisers": "ionizers",
+  "ionises": "ionizes",
+  "ionising": "ionizing",
+  "italicise": "italicize",
+  "italicised": "italicized",
+  "italicises": "italicizes",
+  "italicising": "italicizing",
+  "itemise": "itemize",
+  "itemised": "itemized",
+  "itemises": "itemizes",
+  "itemising": "itemizing",
+  "jeopardise": "jeopardize",
+  "jeopardised": "jeopardized",
+  "jeopardises": "jeopardizes",
+  "jeopardising": "jeopardizing",
+  "jewelled": "jeweled",
+  "jeweller": "jeweler",
+  "jewellers": "jewelers",
+  "jewellery": "jewelry",
+  "judgement": "judgment",
+  "kilogramme": "kilogram",
+  "kilogrammes": "kilograms",
+  "kilometre": "kilometer",
+  "kilometres": "kilometers",
+  "labelled": "labeled",
+  "labelling": "labeling",
+  "labour": "labor",
+  "laboured": "labored",
+  "labourer": "laborer",
+  "labourers": "laborers",
+  "labouring": "laboring",
+  "labours": "labors",
+  "lacklustre": "lackluster",
+  "legalisation": "legalization",
+  "legalise": "legalize",
+  "legalised": "legalized",
+  "legalises": "legalizes",
+  "legalising": "legalizing",
+  "legitimise": "legitimize",
+  "legitimised": "legitimized",
+  "legitimises": "legitimizes",
+  "legitimising": "legitimizing",
+  "leukaemia": "leukemia",
+  "levelled": "leveled",
+  "leveller": "leveler",
+  "levellers": "levelers",
+  "levelling": "leveling",
+  "libelled": "libeled",
+  "libelling": "libeling",
+  "libellous": "libelous",
+  "liberalisation": "liberalization",
+  "liberalise": "liberalize",
+  "liberalised": "liberalized",
+  "liberalises": "liberalizes",
+  "liberalising": "liberalizing",
+  "licence": "license",
+  "licenced": "licensed",
+  "licences": "licenses",
+  "licencing": "licensing",
+  "likeable": "likable",
+  "lionisation": "lionization",
+  "lionise": "lionize",
+  "lionised": "lionized",
+  "lionises": "lionizes",
+  "lionising": "lionizing",
+  "liquidise": "liquidize",
+  "liquidised": "liquidized",
+  "liquidiser": "liquidizer",
+  "liquidisers": "liquidizers",
+  "liquidises": "liquidizes",
+  "liquidising": "liquidizing",
+  "litre": "liter",
+  "litres": "liters",
+  "localise": "localize",
+  "localised": "localized",
+  "localises": "localizes",
+  "localising": "localizing",
+  "louvre": "louver",
+  "louvred": "louvered",
+  "louvres": "louvers",
+  "lustre": "luster",
+  "magnetise": "magnetize",
+  "magnetised": "magnetized",
+  "magnetises": "magnetizes",
+  "magnetising": "magnetizing",
+  "manoeuvrability": "maneuverability",
+  "manoeuvrable": "maneuverable",
+  "manoeuvre": "maneuver",
+  "manoeuvred": "maneuvered",
+  "manoeuvres": "maneuvers",
+  "manoeuvring": "maneuvering",
+  "manoeuvrings": "maneuverings",
+  "marginalisation": "marginalization",
+  "marginalise": "marginalize",
+  "marginalised": "marginalized",
+  "marginalises": "marginalizes",
+  "marginalising": "marginalizing",
+  "marshalled": "marshaled",
+  "marshalling": "marshaling",
+  "marvelled": "marveled",
+  "marvelling": "marveling",
+  "marvellous": "marvelous",
+  "marvellously": "marvelously",
+  "materialisation": "materialization",
+  "materialise": "materialize",
+  "materialised": "materialized",
+  "materialises": "materializes",
+  "materialising": "materializing",
+  "maximisation": "maximization",
+  "maximise": "maximize",
+  "maximised": "maximized",
+  "maximises": "maximizes",
+  "maximising": "maximizing",
+  "meagre": "meager",
+  "mechanisation": "mechanization",
+  "mechanise": "mechanize",
+  "mechanised": "mechanized",
+  "mechanises": "mechanizes",
+  "mechanising": "mechanizing",
+  "mediaeval": "medieval",
+  "memorialise": "memorialize",
+  "memorialised": "memorialized",
+  "memorialises": "memorializes",
+  "memorialising": "memorializing",
+  "memorise": "memorize",
+  "memorised": "memorized",
+  "memorises": "memorizes",
+  "memorising": "memorizing",
+  "mesmerise": "mesmerize",
+  "mesmerised": "mesmerized",
+  "mesmerises": "mesmerizes",
+  "mesmerising": "mesmerizing",
+  "metabolise": "metabolize",
+  "metabolised": "metabolized",
+  "metabolises": "metabolizes",
+  "metabolising": "metabolizing",
+  "metre": "meter",
+  "metres": "meters",
+  "mhm": "hmm",
+  "micrometre": "micrometer",
+  "micrometres": "micrometers",
+  "militarise": "militarize",
+  "militarised": "militarized",
+  "militarises": "militarizes",
+  "militarising": "militarizing",
+  "milligramme": "milligram",
+  "milligrammes": "milligrams",
+  "millilitre": "milliliter",
+  "millilitres": "milliliters",
+  "millimetre": "millimeter",
+  "millimetres": "millimeters",
+  "miniaturisation": "miniaturization",
+  "miniaturise": "miniaturize",
+  "miniaturised": "miniaturized",
+  "miniaturises": "miniaturizes",
+  "miniaturising": "miniaturizing",
+  "minibusses": "minibuses",
+  "minimise": "minimize",
+  "minimised": "minimized",
+  "minimises": "minimizes",
+  "minimising": "minimizing",
+  "misbehaviour": "misbehavior",
+  "misdemeanour": "misdemeanor",
+  "misdemeanours": "misdemeanors",
+  "misspelt": "misspelled",
+  "mitre": "miter",
+  "mitres": "miters",
+  "mm": "hmm",
+  "mmm": "hmm",
+  "mobilisation": "mobilization",
+  "mobilise": "mobilize",
+  "mobilised": "mobilized",
+  "mobilises": "mobilizes",
+  "mobilising": "mobilizing",
+  "modelled": "modeled",
+  "modeller": "modeler",
+  "modellers": "modelers",
+  "modelling": "modeling",
+  "modernise": "modernize",
+  "modernised": "modernized",
+  "modernises": "modernizes",
+  "modernising": "modernizing",
+  "moisturise": "moisturize",
+  "moisturised": "moisturized",
+  "moisturiser": "moisturizer",
+  "moisturisers": "moisturizers",
+  "moisturises": "moisturizes",
+  "moisturising": "moisturizing",
+  "monologue": "monolog",
+  "monologues": "monologs",
+  "monopolisation": "monopolization",
+  "monopolise": "monopolize",
+  "monopolised": "monopolized",
+  "monopolises": "monopolizes",
+  "monopolising": "monopolizing",
+  "moralise": "moralize",
+  "moralised": "moralized",
+  "moralises": "moralizes",
+  "moralising": "moralizing",
+  "motorised": "motorized",
+  "mould": "mold",
+  "moulded": "molded",
+  "moulder": "molder",
+  "mouldered": "moldered",
+  "mouldering": "moldering",
+  "moulders": "molders",
+  "mouldier": "moldier",
+  "mouldiest": "moldiest",
+  "moulding": "molding",
+  "mouldings": "moldings",
+  "moulds": "molds",
+  "mouldy": "moldy",
+  "moult": "molt",
+  "moulted": "molted",
+  "moulting": "molting",
+  "moults": "molts",
+  "moustache": "mustache",
+  "moustached": "mustached",
+  "moustaches": "mustaches",
+  "moustachioed": "mustachioed",
+  "multicoloured": "multicolored",
+  "nationalisation": "nationalization",
+  "nationalisations": "nationalizations",
+  "nationalise": "nationalize",
+  "nationalised": "nationalized",
+  "nationalises": "nationalizes",
+  "nationalising": "nationalizing",
+  "naturalisation": "naturalization",
+  "naturalise": "naturalize",
+  "naturalised": "naturalized",
+  "naturalises": "naturalizes",
+  "naturalising": "naturalizing",
+  "neighbour": "neighbor",
+  "neighbourhood": "neighborhood",
+  "neighbourhoods": "neighborhoods",
+  "neighbouring": "neighboring",
+  "neighbourliness": "neighborliness",
+  "neighbourly": "neighborly",
+  "neighbours": "neighbors",
+  "neutralisation": "neutralization",
+  "neutralise": "neutralize",
+  "neutralised": "neutralized",
+  "neutralises": "neutralizes",
+  "neutralising": "neutralizing",
+  "normalisation": "normalization",
+  "normalise": "normalize",
+  "normalised": "normalized",
+  "normalises": "normalizes",
+  "normalising": "normalizing",
+  "odour": "odor",
+  "odourless": "odorless",
+  "odours": "odors",
+  "oesophagus": "esophagus",
+  "oesophaguses": "esophaguses",
+  "oestrogen": "estrogen",
+  "offence": "offense",
+  "offences": "offenses",
+  "omelette": "omelet",
+  "omelettes": "omelets",
+  "optimise": "optimize",
+  "optimised": "optimized",
+  "optimises": "optimizes",
+  "optimising": "optimizing",
+  "organisation": "organization",
+  "organisational": "organizational",
+  "organisations": "organizations",
+  "organise": "organize",
+  "organised": "organized",
+  "organiser": "organizer",
+  "organisers": "organizers",
+  "organises": "organizes",
+  "organising": "organizing",
+  "orthopaedic": "orthopedic",
+  "orthopaedics": "orthopedics",
+  "ostracise": "ostracize",
+  "ostracised": "ostracized",
+  "ostracises": "ostracizes",
+  "ostracising": "ostracizing",
+  "outmanoeuvre": "outmaneuver",
+  "outmanoeuvred": "outmaneuvered",
+  "outmanoeuvres": "outmaneuvers",
+  "outmanoeuvring": "outmaneuvering",
+  "overemphasise": "overemphasize",
+  "overemphasised": "overemphasized",
+  "overemphasises": "overemphasizes",
+  "overemphasising": "overemphasizing",
+  "oxidisation": "oxidization",
+  "oxidise": "oxidize",
+  "oxidised": "oxidized",
+  "oxidises": "oxidizes",
+  "oxidising": "oxidizing",
+  "paederast": "pederast",
+  "paederasts": "pederasts",
+  "paediatric": "pediatric",
+  "paediatrician": "pediatrician",
+  "paediatricians": "pediatricians",
+  "paediatrics": "pediatrics",
+  "paedophile": "pedophile",
+  "paedophiles": "pedophiles",
+  "paedophilia": "pedophilia",
+  "palaeolithic": "paleolithic",
+  "palaeontologist": "paleontologist",
+  "palaeontologists": "paleontologists",
+  "palaeontology": "paleontology",
+  "panelled": "paneled",
+  "panelling": "paneling",
+  "panellist": "panelist",
+  "panellists": "panelists",
+  "paralyse": "paralyze",
+  "paralysed": "paralyzed",
+  "paralyses": "paralyzes",
+  "paralysing": "paralyzing",
+  "parcelled": "parceled",
+  "parcelling": "parceling",
+  "parlour": "parlor",
+  "parlours": "parlors",
+  "particularise": "particularize",
+  "particularised": "particularized",
+  "particularises": "particularizes",
+  "particularising": "particularizing",
+  "passivisation": "passivization",
+  "passivise": "passivize",
+  "passivised": "passivized",
+  "passivises": "passivizes",
+  "passivising": "passivizing",
+  "pasteurisation": "pasteurization",
+  "pasteurise": "pasteurize",
+  "pasteurised": "pasteurized",
+  "pasteurises": "pasteurizes",
+  "pasteurising": "pasteurizing",
+  "patronise": "patronize",
+  "patronised": "patronized",
+  "patronises": "patronizes",
+  "patronising": "patronizing",
+  "patronisingly": "patronizingly",
+  "pedalled": "pedaled",
+  "pedalling": "pedaling",
+  "pedestrianisation": "pedestrianization",
+  "pedestrianise": "pedestrianize",
+  "pedestrianised": "pedestrianized",
+  "pedestrianises": "pedestrianizes",
+  "pedestrianising": "pedestrianizing",
+  "penalise": "penalize",
+  "penalised": "penalized",
+  "penalises": "penalizes",
+  "penalising": "penalizing",
+  "pencilled": "penciled",
+  "pencilling": "penciling",
+  "personalise": "personalize",
+  "personalised": "personalized",
+  "personalises": "personalizes",
+  "personalising": "personalizing",
+  "pharmacopoeia": "pharmacopeia",
+  "pharmacopoeias": "pharmacopeias",
+  "philosophise": "philosophize",
+  "philosophised": "philosophized",
+  "philosophises": "philosophizes",
+  "philosophising": "philosophizing",
+  "philtre": "filter",
+  "philtres": "filters",
+  "phoney": "phony",
+  "plagiarise": "plagiarize",
+  "plagiarised": "plagiarized",
+  "plagiarises": "plagiarizes",
+  "plagiarising": "plagiarizing",
+  "plough": "plow",
+  "ploughed": "plowed",
+  "ploughing": "plowing",
+  "ploughman": "plowman",
+  "ploughmen": "plowmen",
+  "ploughs": "plows",
+  "ploughshare": "plowshare",
+  "ploughshares": "plowshares",
+  "polarisation": "polarization",
+  "polarise": "polarize",
+  "polarised": "polarized",
+  "polarises": "polarizes",
+  "polarising": "polarizing",
+  "politicisation": "politicization",
+  "politicise": "politicize",
+  "politicised": "politicized",
+  "politicises": "politicizes",
+  "politicising": "politicizing",
+  "popularisation": "popularization",
+  "popularise": "popularize",
+  "popularised": "popularized",
+  "popularises": "popularizes",
+  "popularising": "popularizing",
+  "pouffe": "pouf",
+  "pouffes": "poufs",
+  "practise": "practice",
+  "practised": "practiced",
+  "practises": "practices",
+  "practising": "practicing",
+  "praesidium": "presidium",
+  "praesidiums": "presidiums",
+  "pressurisation": "pressurization",
+  "pressurise": "pressurize",
+  "pressurised": "pressurized",
+  "pressurises": "pressurizes",
+  "pressurising": "pressurizing",
+  "pretence": "pretense",
+  "pretences": "pretenses",
+  "primaeval": "primeval",
+  "prioritisation": "prioritization",
+  "prioritise": "prioritize",
+  "prioritised": "prioritized",
+  "prioritises": "prioritizes",
+  "prioritising": "prioritizing",
+  "privatisation": "privatization",
+  "privatisations": "privatizations",
+  "privatise": "privatize",
+  "privatised": "privatized",
+  "privatises": "privatizes",
+  "privatising": "privatizing",
+  "professionalisation": "professionalization",
+  "professionalise": "professionalize",
+  "professionalised": "professionalized",
+  "professionalises": "professionalizes",
+  "professionalising": "professionalizing",
+  "programme": "program",
+  "programmes": "programs",
+  "prologue": "prolog",
+  "prologues": "prologs",
+  "propagandise": "propagandize",
+  "propagandised": "propagandized",
+  "propagandises": "propagandizes",
+  "propagandising": "propagandizing",
+  "proselytise": "proselytize",
+  "proselytised": "proselytized",
+  "proselytiser": "proselytizer",
+  "proselytisers": "proselytizers",
+  "proselytises": "proselytizes",
+  "proselytising": "proselytizing",
+  "psychoanalyse": "psychoanalyze",
+  "psychoanalysed": "psychoanalyzed",
+  "psychoanalyses": "psychoanalyzes",
+  "psychoanalysing": "psychoanalyzing",
+  "publicise": "publicize",
+  "publicised": "publicized",
+  "publicises": "publicizes",
+  "publicising": "publicizing",
+  "pulverisation": "pulverization",
+  "pulverise": "pulverize",
+  "pulverised": "pulverized",
+  "pulverises": "pulverizes",
+  "pulverising": "pulverizing",
+  "pummelled": "pummel",
+  "pummelling": "pummeled",
+  "pyjama": "pajama",
+  "pyjamas": "pajamas",
+  "pzazz": "pizzazz",
+  "quarrelled": "quarreled",
+  "quarrelling": "quarreling",
+  "radicalise": "radicalize",
+  "radicalised": "radicalized",
+  "radicalises": "radicalizes",
+  "radicalising": "radicalizing",
+  "rancour": "rancor",
+  "randomise": "randomize",
+  "randomised": "randomized",
+  "randomises": "randomizes",
+  "randomising": "randomizing",
+  "rationalisation": "rationalization",
+  "rationalisations": "rationalizations",
+  "rationalise": "rationalize",
+  "rationalised": "rationalized",
+  "rationalises": "rationalizes",
+  "rationalising": "rationalizing",
+  "ravelled": "raveled",
+  "ravelling": "raveling",
+  "realisable": "realizable",
+  "realisation": "realization",
+  "realisations": "realizations",
+  "realise": "realize",
+  "realised": "realized",
+  "realises": "realizes",
+  "realising": "realizing",
+  "recognisable": "recognizable",
+  "recognisably": "recognizably",
+  "recognisance": "recognizance",
+  "recognise": "recognize",
+  "recognised": "recognized",
+  "recognises": "recognizes",
+  "recognising": "recognizing",
+  "reconnoitre": "reconnoiter",
+  "reconnoitred": "reconnoitered",
+  "reconnoitres": "reconnoiters",
+  "reconnoitring": "reconnoitering",
+  "refuelled": "refueled",
+  "refuelling": "refueling",
+  "regularisation": "regularization",
+  "regularise": "regularize",
+  "regularised": "regularized",
+  "regularises": "regularizes",
+  "regularising": "regularizing",
+  "remodelled": "remodeled",
+  "remodelling": "remodeling",
+  "remould": "remold",
+  "remoulded": "remolded",
+  "remoulding": "remolding",
+  "remoulds": "remolds",
+  "reorganisation": "reorganization",
+  "reorganisations": "reorganizations",
+  "reorganise": "reorganize",
+  "reorganised": "reorganized",
+  "reorganises": "reorganizes",
+  "reorganising": "reorganizing",
+  "revelled": "reveled",
+  "reveller": "reveler",
+  "revellers": "revelers",
+  "revelling": "reveling",
+  "revitalise": "revitalize",
+  "revitalised": "revitalized",
+  "revitalises": "revitalizes",
+  "revitalising": "revitalizing",
+  "revolutionise": "revolutionize",
+  "revolutionised": "revolutionized",
+  "revolutionises": "revolutionizes",
+  "revolutionising": "revolutionizing",
+  "rhapsodise": "rhapsodize",
+  "rhapsodised": "rhapsodized",
+  "rhapsodises": "rhapsodizes",
+  "rhapsodising": "rhapsodizing",
+  "rigour": "rigor",
+  "rigours": "rigors",
+  "ritualised": "ritualized",
+  "rivalled": "rivaled",
+  "rivalling": "rivaling",
+  "romanticise": "romanticize",
+  "romanticised": "romanticized",
+  "romanticises": "romanticizes",
+  "romanticising": "romanticizing",
+  "rumour": "rumor",
+  "rumoured": "rumored",
+  "rumours": "rumors",
+  "sabre": "saber",
+  "sabres": "sabers",
+  "saltpetre": "saltpeter",
+  "sanitise": "sanitize",
+  "sanitised": "sanitized",
+  "sanitises": "sanitizes",
+  "sanitising": "sanitizing",
+  "satirise": "satirize",
+  "satirised": "satirized",
+  "satirises": "satirizes",
+  "satirising": "satirizing",
+  "saviour": "savior",
+  "saviours": "saviors",
+  "savour": "savor",
+  "savoured": "savored",
+  "savouries": "savories",
+  "savouring": "savoring",
+  "savours": "savors",
+  "savoury": "savory",
+  "scandalise": "scandalize",
+  "scandalised": "scandalized",
+  "scandalises": "scandalizes",
+  "scandalising": "scandalizing",
+  "sceptic": "skeptic",
+  "sceptical": "skeptical",
+  "sceptically": "skeptically",
+  "scepticism": "skepticism",
+  "sceptics": "skeptics",
+  "sceptre": "scepter",
+  "sceptres": "scepters",
+  "scrutinise": "scrutinize",
+  "scrutinised": "scrutinized",
+  "scrutinises": "scrutinizes",
+  "scrutinising": "scrutinizing",
+  "secularisation": "secularization",
+  "secularise": "secularize",
+  "secularised": "secularized",
+  "secularises": "secularizes",
+  "secularising": "secularizing",
+  "sensationalise": "sensationalize",
+  "sensationalised": "sensationalized",
+  "sensationalises": "sensationalizes",
+  "sensationalising": "sensationalizing",
+  "sensitise": "sensitize",
+  "sensitised": "sensitized",
+  "sensitises": "sensitizes",
+  "sensitising": "sensitizing",
+  "sentimentalise": "sentimentalize",
+  "sentimentalised": "sentimentalized",
+  "sentimentalises": "sentimentalizes",
+  "sentimentalising": "sentimentalizing",
+  "sepulchre": "sepulcher",
+  "sepulchres": "sepulchers",
+  "serialisation": "serialization",
+  "serialisations": "serializations",
+  "serialise": "serialize",
+  "serialised": "serialized",
+  "serialises": "serializes",
+  "serialising": "serializing",
+  "sermonise": "sermonize",
+  "sermonised": "sermonized",
+  "sermonises": "sermonizes",
+  "sermonising": "sermonizing",
+  "sheikh": "sheik",
+  "shovelled": "shoveled",
+  "shovelling": "shoveling",
+  "shrivelled": "shriveled",
+  "shrivelling": "shriveling",
+  "signalise": "signalize",
+  "signalised": "signalized",
+  "signalises": "signalizes",
+  "signalising": "signalizing",
+  "signalled": "signaled",
+  "signalling": "signaling",
+  "smoulder": "smolder",
+  "smouldered": "smoldered",
+  "smouldering": "smoldering",
+  "smoulders": "smolders",
+  "snivelled": "sniveled",
+  "snivelling": "sniveling",
+  "snorkelled": "snorkeled",
+  "snorkelling": "snorkeling",
+  "snowplough": "snowplow",
+  "snowploughs": "snowplow",
+  "socialisation": "socialization",
+  "socialise": "socialize",
+  "socialised": "socialized",
+  "socialises": "socializes",
+  "socialising": "socializing",
+  "sodomise": "sodomize",
+  "sodomised": "sodomized",
+  "sodomises": "sodomizes",
+  "sodomising": "sodomizing",
+  "solemnise": "solemnize",
+  "solemnised": "solemnized",
+  "solemnises": "solemnizes",
+  "solemnising": "solemnizing",
+  "sombre": "somber",
+  "specialisation": "specialization",
+  "specialisations": "specializations",
+  "specialise": "specialize",
+  "specialised": "specialized",
+  "specialises": "specializes",
+  "specialising": "specializing",
+  "spectre": "specter",
+  "spectres": "specters",
+  "spiralled": "spiraled",
+  "spiralling": "spiraling",
+  "splendour": "splendor",
+  "splendours": "splendors",
+  "squirrelled": "squirreled",
+  "squirrelling": "squirreling",
+  "stabilisation": "stabilization",
+  "stabilise": "stabilize",
+  "stabilised": "stabilized",
+  "stabiliser": "stabilizer",
+  "stabilisers": "stabilizers",
+  "stabilises": "stabilizes",
+  "stabilising": "stabilizing",
+  "standardisation": "standardization",
+  "standardise": "standardize",
+  "standardised": "standardized",
+  "standardises": "standardizes",
+  "standardising": "standardizing",
+  "stencilled": "stenciled",
+  "stencilling": "stenciling",
+  "sterilisation": "sterilization",
+  "sterilisations": "sterilizations",
+  "sterilise": "sterilize",
+  "sterilised": "sterilized",
+  "steriliser": "sterilizer",
+  "sterilisers": "sterilizers",
+  "sterilises": "sterilizes",
+  "sterilising": "sterilizing",
+  "stigmatisation": "stigmatization",
+  "stigmatise": "stigmatize",
+  "stigmatised": "stigmatized",
+  "stigmatises": "stigmatizes",
+  "stigmatising": "stigmatizing",
+  "storey": "story",
+  "storeys": "stories",
+  "subsidisation": "subsidization",
+  "subsidise": "subsidize",
+  "subsidised": "subsidized",
+  "subsidiser": "subsidizer",
+  "subsidisers": "subsidizers",
+  "subsidises": "subsidizes",
+  "subsidising": "subsidizing",
+  "succour": "succor",
+  "succoured": "succored",
+  "succouring": "succoring",
+  "succours": "succors",
+  "sulphate": "sulfate",
+  "sulphates": "sulfates",
+  "sulphide": "sulfide",
+  "sulphides": "sulfides",
+  "sulphur": "sulfur",
+  "sulphurous": "sulfurous",
+  "summarise": "summarize",
+  "summarised": "summarized",
+  "summarises": "summarizes",
+  "summarising": "summarizing",
+  "swivelled": "swiveled",
+  "swivelling": "swiveling",
+  "symbolise": "symbolize",
+  "symbolised": "symbolized",
+  "symbolises": "symbolizes",
+  "symbolising": "symbolizing",
+  "sympathise": "sympathize",
+  "sympathised": "sympathized",
+  "sympathiser": "sympathizer",
+  "sympathisers": "sympathizers",
+  "sympathises": "sympathizes",
+  "sympathising": "sympathizing",
+  "synchronisation": "synchronization",
+  "synchronise": "synchronize",
+  "synchronised": "synchronized",
+  "synchronises": "synchronizes",
+  "synchronising": "synchronizing",
+  "synthesise": "synthesize",
+  "synthesised": "synthesized",
+  "synthesiser": "synthesizer",
+  "synthesisers": "synthesizers",
+  "synthesises": "synthesizes",
+  "synthesising": "synthesizing",
+  "syphon": "siphon",
+  "syphoned": "siphoned",
+  "syphoning": "siphoning",
+  "syphons": "siphons",
+  "systematisation": "systematization",
+  "systematise": "systematize",
+  "systematised": "systematized",
+  "systematises": "systematizes",
+  "systematising": "systematizing",
+  "tantalise": "tantalize",
+  "tantalised": "tantalized",
+  "tantalises": "tantalizes",
+  "tantalising": "tantalizing",
+  "tantalisingly": "tantalizingly",
+  "tasselled": "tasseled",
+  "technicolour": "technicolor",
+  "temporise": "temporize",
+  "temporised": "temporized",
+  "temporises": "temporizes",
+  "temporising": "temporizing",
+  "tenderise": "tenderize",
+  "tenderised": "tenderized",
+  "tenderises": "tenderizes",
+  "tenderising": "tenderizing",
+  "terrorise": "terrorize",
+  "terrorised": "terrorized",
+  "terrorises": "terrorizes",
+  "terrorising": "terrorizing",
+  "theatre": "theater",
+  "theatregoer": "theatergoer",
+  "theatregoers": "theatergoers",
+  "theatres": "theaters",
+  "theorise": "theorize",
+  "theorised": "theorized",
+  "theorises": "theorizes",
+  "theorising": "theorizing",
+  "tonne": "ton",
+  "tonnes": "tons",
+  "towelled": "toweled",
+  "towelling": "toweling",
+  "toxaemia": "toxemia",
+  "tranquillise": "tranquilize",
+  "tranquillised": "tranquilized",
+  "tranquilliser": "tranquilizer",
+  "tranquillisers": "tranquilizers",
+  "tranquillises": "tranquilizes",
+  "tranquillising": "tranquilizing",
+  "tranquillity": "tranquility",
+  "tranquillize": "tranquilize",
+  "tranquillized": "tranquilized",
+  "tranquillizer": "tranquilizer",
+  "tranquillizers": "tranquilizers",
+  "tranquillizes": "tranquilizes",
+  "tranquillizing": "tranquilizing",
+  "tranquilly": "tranquility",
+  "transistorised": "transistorized",
+  "traumatise": "traumatize",
+  "traumatised": "traumatized",
+  "traumatises": "traumatizes",
+  "traumatising": "traumatizing",
+  "travelled": "traveled",
+  "traveller": "traveler",
+  "travellers": "travelers",
+  "travelling": "traveling",
+  "travelog": "travelogue",
+  "travelogs": "travelogues",
+  "trialled": "trialed",
+  "trialling": "trialing",
+  "tricolour": "tricolor",
+  "tricolours": "tricolors",
+  "trivialise": "trivialize",
+  "trivialised": "trivialized",
+  "trivialises": "trivializes",
+  "trivialising": "trivializing",
+  "tumour": "tumor",
+  "tumours": "tumors",
+  "tunnelled": "tunneled",
+  "tunnelling": "tunneling",
+  "tyrannise": "tyrannize",
+  "tyrannised": "tyrannized",
+  "tyrannises": "tyrannizes",
+  "tyrannising": "tyrannizing",
+  "tyre": "tire",
+  "tyres": "tires",
+  "unauthorised": "unauthorized",
+  "uncivilised": "uncivilized",
+  "underutilised": "underutilized",
+  "unequalled": "unequaled",
+  "unfavourable": "unfavorable",
+  "unfavourably": "unfavorably",
+  "unionisation": "unionization",
+  "unionise": "unionize",
+  "unionised": "unionized",
+  "unionises": "unionizes",
+  "unionising": "unionizing",
+  "unorganised": "unorganized",
+  "unravelled": "unraveled",
+  "unravelling": "unraveling",
+  "unrecognisable": "unrecognizable",
+  "unrecognised": "unrecognized",
+  "unrivalled": "unrivaled",
+  "unsavoury": "unsavory",
+  "untrammelled": "untrammeled",
+  "urbanisation": "urbanization",
+  "urbanise": "urbanize",
+  "urbanised": "urbanized",
+  "urbanises": "urbanizes",
+  "urbanising": "urbanizing",
+  "utilisable": "utilizable",
+  "utilisation": "utilization",
+  "utilise": "utilize",
+  "utilised": "utilized",
+  "utilises": "utilizes",
+  "utilising": "utilizing",
+  "valour": "valor",
+  "vandalise": "vandalize",
+  "vandalised": "vandalized",
+  "vandalises": "vandalizes",
+  "vandalising": "vandalizing",
+  "vaporisation": "vaporization",
+  "vaporise": "vaporize",
+  "vaporised": "vaporized",
+  "vaporises": "vaporizes",
+  "vaporising": "vaporizing",
+  "vapour": "vapor",
+  "vapours": "vapors",
+  "verbalise": "verbalize",
+  "verbalised": "verbalized",
+  "verbalises": "verbalizes",
+  "verbalising": "verbalizing",
+  "victimisation": "victimization",
+  "victimise": "victimize",
+  "victimised": "victimized",
+  "victimises": "victimizes",
+  "victimising": "victimizing",
+  "videodisc": "videodisk",
+  "videodiscs": "videodisks",
+  "vigour": "vigor",
+  "visualisation": "visualization",
+  "visualisations": "visualizations",
+  "visualise": "visualize",
+  "visualised": "visualized",
+  "visualises": "visualizes",
+  "visualising": "visualizing",
+  "vocalisation": "vocalization",
+  "vocalisations": "vocalizations",
+  "vocalise": "vocalize",
+  "vocalised": "vocalized",
+  "vocalises": "vocalizes",
+  "vocalising": "vocalizing",
+  "vulcanised": "vulcanized",
+  "vulgarisation": "vulgarization",
+  "vulgarise": "vulgarize",
+  "vulgarised": "vulgarized",
+  "vulgarises": "vulgarizes",
+  "vulgarising": "vulgarizing",
+  "waggon": "wagon",
+  "waggons": "wagons",
+  "watercolour": "watercolor",
+  "watercolours": "watercolors",
+  "weaselled": "weaseled",
+  "weaselling": "weaseling",
+  "westernisation": "westernization",
+  "westernise": "westernize",
+  "westernised": "westernized",
+  "westernises": "westernizes",
+  "westernising": "westernizing",
+  "womanise": "womanize",
+  "womanised": "womanized",
+  "womaniser": "womanizer",
+  "womanisers": "womanizers",
+  "womanises": "womanizes",
+  "womanising": "womanizing",
+  "woollen": "woolen",
+  "woollens": "woolens",
+  "woollies": "woolies",
+  "woolly": "wooly",
+  "worshipped": "worshiped",
+  "worshipper": "worshiper",
+  "worshipping": "worshiping",
+  "yodelled": "yodeled",
+  "yodelling": "yodeling",
+  "yoghourt": "yogurt",
+  "yoghourts": "yogurts",
+  "yoghurt": "yogurt",
+  "yoghurts": "yogurts"
+}
diff --git a/benchmark/requirements.benchmark.txt b/benchmark/requirements.benchmark.txt
new file mode 100644
index 0000000..2645004
--- /dev/null
+++ b/benchmark/requirements.benchmark.txt
@@ -0,0 +1,6 @@
+transformers
+jiwer
+evaluate
+datasets
+memory_profiler
+py3nvml
diff --git a/benchmark/speed_benchmark.py b/benchmark/speed_benchmark.py
new file mode 100644
index 0000000..a3d6ffb
--- /dev/null
+++ b/benchmark/speed_benchmark.py
@@ -0,0 +1,31 @@
+import argparse
+import timeit
+
+from typing import Callable
+
+from utils import inference
+
+parser = argparse.ArgumentParser(description="Speed benchmark")
+parser.add_argument(
+    "--repeat",
+    type=int,
+    default=3,
+    help="Times an experiment will be run.",
+)
+args = parser.parse_args()
+
+
+def measure_speed(func: Callable[[], None]):
+    # as written in https://docs.python.org/3/library/timeit.html#timeit.Timer.repeat,
+    # min should be taken rather than the average
+    runtimes = timeit.repeat(
+        func,
+        repeat=args.repeat,
+        number=10,
+    )
+    print(runtimes)
+    print("Min execution time: %.3fs" % (min(runtimes) / 10.0))
+
+
+if __name__ == "__main__":
+    measure_speed(inference)
diff --git a/benchmark/utils.py b/benchmark/utils.py
new file mode 100644
index 0000000..8e5ac46
--- /dev/null
+++ b/benchmark/utils.py
@@ -0,0 +1,39 @@
+import logging
+
+from threading import Thread
+from typing import Optional
+
+from faster_whisper import WhisperModel
+
+model_path = "large-v3"
+model = WhisperModel(model_path, device="cuda")
+
+
+def inference():
+    segments, info = model.transcribe("benchmark.m4a", language="fr")
+    for segment in segments:
+        print("[%.2fs -> %.2fs] %s" % (segment.start, segment.end, segment.text))
+
+
+def get_logger(name: Optional[str] = None) -> logging.Logger:
+    formatter = logging.Formatter("%(levelname)s: %(message)s")
+    logger = logging.getLogger(name)
+    logger.setLevel(logging.DEBUG)
+    handler = logging.StreamHandler()
+    handler.setFormatter(formatter)
+    logger.addHandler(handler)
+    return logger
+
+
+class MyThread(Thread):
+    def __init__(self, func, params):
+        super(MyThread, self).__init__()
+        self.func = func
+        self.params = params
+        self.result = None
+
+    def run(self):
+        self.result = self.func(*self.params)
+
+    def get_result(self):
+        return self.result
diff --git a/benchmark/wer_benchmark.py b/benchmark/wer_benchmark.py
new file mode 100644
index 0000000..bf0a1e0
--- /dev/null
+++ b/benchmark/wer_benchmark.py
@@ -0,0 +1,61 @@
+import argparse
+import json
+
+from datasets import load_dataset
+from evaluate import load
+from tqdm import tqdm
+from transformers.models.whisper.english_normalizer import EnglishTextNormalizer
+
+from faster_whisper import WhisperModel
+
+parser = argparse.ArgumentParser(description="WER benchmark")
+parser.add_argument(
+    "--audio_numb",
+    type=int,
+    default=None,
+    help="Specify the number of validation audio files in the dataset."
+    " Set to None to retrieve all audio files.",
+)
+args = parser.parse_args()
+
+model_path = "large-v3"
+model = WhisperModel(model_path, device="cuda")
+
+# load the dataset with streaming mode
+dataset = load_dataset("librispeech_asr", "clean", split="validation", streaming=True)
+
+# define the evaluation metric
+wer_metric = load("wer")
+normalizer = EnglishTextNormalizer(json.load(open("normalizer.json")))
+
+
+def inference(batch):
+    batch["transcription"] = []
+    for sample in batch["audio"]:
+        segments, info = model.transcribe(sample["array"], language="en")
+        batch["transcription"].append("".join([segment.text for segment in segments]))
+    batch["reference"] = batch["text"]
+    return batch
+
+
+dataset = dataset.map(function=inference, batched=True, batch_size=16)
+
+all_transcriptions = []
+all_references = []
+
+# iterate over the dataset and run inference
+for i, result in tqdm(enumerate(dataset), desc="Evaluating..."):
+    all_transcriptions.append(result["transcription"])
+    all_references.append(result["reference"])
+    if args.audio_numb and i == (args.audio_numb - 1):
+        break
+
+# normalize predictions and references
+all_transcriptions = [normalizer(transcription) for transcription in all_transcriptions]
+all_references = [normalizer(reference) for reference in all_references]
+
+# compute the WER metric
+wer = 100 * wer_metric.compute(
+    predictions=all_transcriptions, references=all_references
+)
+print("WER: %.3f" % wer)
diff --git a/docker/Dockerfile b/docker/Dockerfile
new file mode 100644
index 0000000..604c8e1
--- /dev/null
+++ b/docker/Dockerfile
@@ -0,0 +1,6 @@
+FROM nvidia/cuda:12.2.2-cudnn8-runtime-ubuntu22.04
+WORKDIR /root
+RUN apt-get update -y && apt-get install -y python3-pip
+COPY infer.py jfk.flac ./
+RUN pip3 install faster-whisper
+CMD ["python3", "infer.py"]
diff --git a/docker/infer.py b/docker/infer.py
new file mode 100644
index 0000000..5d6b12c
--- /dev/null
+++ b/docker/infer.py
@@ -0,0 +1,7 @@
+from faster_whisper import WhisperModel
+
+jfk_path = "jfk.flac"
+model = WhisperModel("tiny", device="cuda")
+segments, info = model.transcribe(jfk_path, word_timestamps=True)
+for segment in segments:
+    print("[%.2fs -> %.2fs] %s" % (segment.start, segment.end, segment.text))
diff --git a/docker/jfk.flac b/docker/jfk.flac
new file mode 100644
index 0000000..e44b7c1
Binary files /dev/null and b/docker/jfk.flac differ
diff --git a/faster_whisper/assets/silero_vad.onnx b/faster_whisper/assets/silero_vad.onnx
index 5c21912..d0ccd9d 100644
Binary files a/faster_whisper/assets/silero_vad.onnx and b/faster_whisper/assets/silero_vad.onnx differ
diff --git a/faster_whisper/tokenizer.py b/faster_whisper/tokenizer.py
index c3b13b4..3bf76a5 100644
--- a/faster_whisper/tokenizer.py
+++ b/faster_whisper/tokenizer.py
@@ -105,6 +105,42 @@ class Tokenizer:
             [s if isinstance(s, str) else self.tokenizer.decode(s) for s in outputs]
         )
 
+    @cached_property
+    def non_speech_tokens(self) -> Tuple[int]:
+        """
+        Returns the list of tokens to suppress in order to avoid any speaker tags or non-speech
+        annotations, to prevent sampling texts that are not actually spoken in the audio, e.g.
+
+        - ♪♪♪
+        - ( SPEAKING FOREIGN LANGUAGE )
+        - [DAVID] Hey there,
+
+        keeping basic punctuations like commas, periods, question marks, exclamation points, etc.
+        """
+        symbols = list('"#()*+/:;<=>@[\\]^_`{|}~「」『』')
+        symbols += (
+            "<< >> <<< >>> -- --- -( -[ (' (\" (( )) ((( ))) [[ ]] {{ }} ♪♪ ♪♪♪".split()
+        )
+
+        # symbols that may be a single token or multiple tokens depending on the tokenizer.
+        # In case they're multiple tokens, suppress the first token, which is safe because:
+        # These are between U+2640 and U+267F miscellaneous symbols that are okay to suppress
+        # in generations, and in the 3-byte UTF-8 representation they share the first two bytes.
+        miscellaneous = set("♩♪♫♬♭♮♯")
+        assert all(0x2640 <= ord(c) <= 0x267F for c in miscellaneous)
+
+        # allow hyphens "-" and single quotes "'" between words, but not at the beginning of a word
+        result = {self.encode(" -")[0], self.encode(" '")[0]}
+        for symbol in symbols + list(miscellaneous):
+            for tokens in [
+                self.encode(symbol),
+                self.encode(" " + symbol),
+            ]:
+                if len(tokens) == 1 or symbol in miscellaneous:
+                    result.add(tokens[0])
+
+        return tuple(sorted(result))
+
     def split_to_word_tokens(
         self, tokens: List[int]
     ) -> Tuple[List[str], List[List[int]]]:
diff --git a/faster_whisper/transcribe.py b/faster_whisper/transcribe.py
index db2121f..44959b1 100644
--- a/faster_whisper/transcribe.py
+++ b/faster_whisper/transcribe.py
@@ -69,6 +69,7 @@ class TranscriptionOptions(NamedTuple):
     max_new_tokens: Optional[int]
     clip_timestamps: Union[str, List[float]]
     hallucination_silence_threshold: Optional[float]
+    hotwords: Optional[str]
 
 
 class TranscriptionInfo(NamedTuple):
@@ -92,12 +93,15 @@ class WhisperModel:
         num_workers: int = 1,
         download_root: Optional[str] = None,
         local_files_only: bool = False,
+        files: dict = None,
+        **model_kwargs,
     ):
         """Initializes the Whisper model.
 
         Args:
           model_size_or_path: Size of the model to use (tiny, tiny.en, base, base.en,
-            small, small.en, medium, medium.en, large-v1, large-v2, large-v3, or large), a path to a
+            small, small.en, distil-small.en, medium, medium.en, distil-medium.en, large-v1,
+            large-v2, large-v3, large, distil-large-v2 or distil-large-v3), a path to a
             converted model directory, or a CTranslate2-converted Whisper model ID from the HF Hub.
             When a size or a model ID is configured, the converted model is downloaded
             from the Hugging Face Hub.
@@ -118,10 +122,18 @@ class WhisperModel:
             are saved in the standard Hugging Face cache directory.
           local_files_only:  If True, avoid downloading the file and return the path to the
             local cached file if it exists.
+          files: Load model files from the memory. This argument is a dictionary mapping file names
+            to file contents as file-like or bytes objects. If this is set, model_path acts as an
+            identifier for this model.
         """
         self.logger = get_logger()
 
-        if os.path.isdir(model_size_or_path):
+        tokenizer_bytes, preprocessor_bytes = None, None
+        if files:
+            model_path = model_size_or_path
+            tokenizer_bytes = files.pop("tokenizer.json", None)
+            preprocessor_bytes = files.pop("preprocessor_config.json", None)
+        elif os.path.isdir(model_size_or_path):
             model_path = model_size_or_path
         else:
             model_path = download_model(
@@ -137,17 +149,20 @@ class WhisperModel:
             compute_type=compute_type,
             intra_threads=cpu_threads,
             inter_threads=num_workers,
+            files=files,
+            **model_kwargs,
         )
 
         tokenizer_file = os.path.join(model_path, "tokenizer.json")
-        if os.path.isfile(tokenizer_file):
+        if tokenizer_bytes:
+            self.hf_tokenizer = tokenizers.Tokenizer.from_buffer(tokenizer_bytes)
+        elif os.path.isfile(tokenizer_file):
             self.hf_tokenizer = tokenizers.Tokenizer.from_file(tokenizer_file)
         else:
             self.hf_tokenizer = tokenizers.Tokenizer.from_pretrained(
                 "openai/whisper-tiny" + ("" if self.model.is_multilingual else ".en")
             )
-
-        self.feat_kwargs = self._get_feature_kwargs(model_path)
+        self.feat_kwargs = self._get_feature_kwargs(model_path, preprocessor_bytes)
         self.feature_extractor = FeatureExtractor(**self.feat_kwargs)
         self.num_samples_per_token = self.feature_extractor.hop_length * 2
         self.frames_per_second = (
@@ -165,19 +180,21 @@ class WhisperModel:
         """The languages supported by the model."""
         return list(_LANGUAGE_CODES) if self.model.is_multilingual else ["en"]
 
-    def _get_feature_kwargs(self, model_path) -> dict:
-        preprocessor_config_file = os.path.join(model_path, "preprocessor_config.json")
+    def _get_feature_kwargs(self, model_path, preprocessor_bytes=None) -> dict:
         config = {}
-        if os.path.isfile(preprocessor_config_file):
-            try:
-                with open(preprocessor_config_file, "r", encoding="utf-8") as json_file:
-                    config = json.load(json_file)
-                valid_keys = signature(FeatureExtractor.__init__).parameters.keys()
-                config = {k: v for k, v in config.items() if k in valid_keys}
-            except json.JSONDecodeError as e:
-                self.logger.warning(
-                    "Could not load preprocessor_config.json: %s", str(e)
-                )
+        try:
+            config_path = os.path.join(model_path, "preprocessor_config.json")
+            if preprocessor_bytes:
+                config = json.loads(preprocessor_bytes)
+            elif os.path.isfile(config_path):
+                with open(config_path, "r", encoding="utf-8") as file:
+                    config = json.load(file)
+            else:
+                return config
+            valid_keys = signature(FeatureExtractor.__init__).parameters.keys()
+            return {k: v for k, v in config.items() if k in valid_keys}
+        except json.JSONDecodeError as e:
+            self.logger.warning("Could not load preprocessor config: %s", e)
 
         return config
 
@@ -220,6 +237,7 @@ class WhisperModel:
         chunk_length: Optional[int] = None,
         clip_timestamps: Union[str, List[float]] = "0",
         hallucination_silence_threshold: Optional[float] = None,
+        hotwords: Optional[str] = None,
         language_detection_threshold: Optional[float] = None,
         language_detection_segments: int = 1,
     ) -> Tuple[Iterable[Segment], TranscriptionInfo]:
@@ -259,7 +277,7 @@ class WhisperModel:
           prefix: Optional text to provide as a prefix for the first window.
           suppress_blank: Suppress blank outputs at the beginning of the sampling.
           suppress_tokens: List of token IDs to suppress. -1 will suppress a default set
-            of symbols as defined in the model config.json file.
+            of symbols as defined in `tokenizer.non_speech_tokens()`
           without_timestamps: Only sample text tokens.
           max_initial_timestamp: The initial timestamp cannot be later than this.
           word_timestamps: Extract word-level timestamps using the cross-attention pattern
@@ -277,17 +295,18 @@ class WhisperModel:
             the maximum will be set by the default max_length.
           chunk_length: The length of audio segments. If it is not None, it will overwrite the
             default chunk_length of the FeatureExtractor.
-          clip_timestamps: Union[str, List[float]]
+          clip_timestamps:
             Comma-separated list start,end,start,end,... timestamps (in seconds) of clips to
              process. The last end timestamp defaults to the end of the file.
              vad_filter will be ignored if clip_timestamps is used.
-          hallucination_silence_threshold: Optional[float]
+          hallucination_silence_threshold:
             When word_timestamps is True, skip silent periods longer than this threshold
              (in seconds) when a possible hallucination is detected
+          hotwords:
+            Hotwords/hint phrases to provide the model with. Has no effect if prefix is not None.
           language_detection_threshold: If the maximum probability of the language tokens is higher
            than this value, the language is detected.
           language_detection_segments: Number of segments to consider for the language detection.
-
         Returns:
           A tuple with:
 
@@ -351,16 +370,27 @@ class WhisperModel:
                     or language_detection_segments < 1
                 ):
                     language_detection_segments = 1
-                seek = 0
-                detected_language_info = {}
+                start_timestamp = (
+                    float(clip_timestamps.split(",")[0])
+                    if isinstance(clip_timestamps, str)
+                    else clip_timestamps[0]
+                )
                 content_frames = (
                     features.shape[-1] - self.feature_extractor.nb_max_frames
                 )
-                while (
-                    seek <= content_frames
-                    and seek
-                    < self.feature_extractor.nb_max_frames * language_detection_segments
-                ):
+                seek = (
+                    int(start_timestamp * self.frames_per_second)
+                    if start_timestamp * self.frames_per_second < content_frames
+                    else 0
+                )
+                end_frames = min(
+                    seek
+                    + self.feature_extractor.nb_max_frames
+                    * language_detection_segments,
+                    content_frames,
+                )
+                detected_language_info = {}
+                while seek <= end_frames:
                     segment = features[
                         :, seek : seek + self.feature_extractor.nb_max_frames
                     ]
@@ -432,7 +462,11 @@ class WhisperModel:
             initial_prompt=initial_prompt,
             prefix=prefix,
             suppress_blank=suppress_blank,
-            suppress_tokens=get_suppressed_tokens(tokenizer, suppress_tokens),
+            suppress_tokens=(
+                get_suppressed_tokens(tokenizer, suppress_tokens)
+                if suppress_tokens
+                else suppress_tokens
+            ),
             without_timestamps=without_timestamps,
             max_initial_timestamp=max_initial_timestamp,
             word_timestamps=word_timestamps,
@@ -441,6 +475,7 @@ class WhisperModel:
             max_new_tokens=max_new_tokens,
             clip_timestamps=clip_timestamps,
             hallucination_silence_threshold=hallucination_silence_threshold,
+            hotwords=hotwords,
         )
 
         segments = self.generate_segments(features, tokenizer, options, encoder_output)
@@ -457,7 +492,6 @@ class WhisperModel:
             vad_options=vad_parameters,
             all_language_probs=all_language_probs,
         )
-
         return segments, info
 
     def generate_segments(
@@ -471,14 +505,16 @@ class WhisperModel:
         content_duration = float(content_frames * self.feature_extractor.time_per_frame)
 
         if isinstance(options.clip_timestamps, str):
-            TranscriptionOptions.clip_timestamps = [
-                float(ts)
-                for ts in (
-                    options.clip_timestamps.split(",")
-                    if options.clip_timestamps
-                    else []
-                )
-            ]
+            options = options._replace(
+                clip_timestamps=[
+                    float(ts)
+                    for ts in (
+                        options.clip_timestamps.split(",")
+                        if options.clip_timestamps
+                        else []
+                    )
+                ]
+            )
         seek_points: List[int] = [
             round(ts * self.frames_per_second) for ts in options.clip_timestamps
         ]
@@ -548,6 +584,7 @@ class WhisperModel:
                 previous_tokens,
                 without_timestamps=options.without_timestamps,
                 prefix=options.prefix if seek == 0 else None,
+                hotwords=options.hotwords,
             )
 
             if seek > 0 or encoder_output is None:
@@ -948,12 +985,19 @@ class WhisperModel:
         previous_tokens: List[int],
         without_timestamps: bool = False,
         prefix: Optional[str] = None,
+        hotwords: Optional[str] = None,
     ) -> List[int]:
         prompt = []
 
-        if previous_tokens:
+        if previous_tokens or (hotwords and not prefix):
             prompt.append(tokenizer.sot_prev)
-            prompt.extend(previous_tokens[-(self.max_length // 2 - 1) :])
+            if hotwords and not prefix:
+                hotwords_tokens = tokenizer.encode(" " + hotwords.strip())
+                if len(hotwords_tokens) >= self.max_length // 2:
+                    hotwords_tokens = hotwords_tokens[: self.max_length // 2 - 1]
+                prompt.extend(hotwords_tokens)
+            if previous_tokens:
+                prompt.extend(previous_tokens[-(self.max_length // 2 - 1) :])
 
         prompt.extend(tokenizer.sot_sequence)
 
@@ -1195,15 +1239,16 @@ def get_compression_ratio(text: str) -> float:
 
 def get_suppressed_tokens(
     tokenizer: Tokenizer,
-    suppress_tokens: Optional[List[int]],
+    suppress_tokens: Tuple[int],
 ) -> Optional[List[int]]:
-    if not suppress_tokens or -1 in suppress_tokens:
-        return suppress_tokens
+    if -1 in suppress_tokens:
+        suppress_tokens = [t for t in suppress_tokens if t >= 0]
+        suppress_tokens.extend(tokenizer.non_speech_tokens)
+    elif suppress_tokens is None or len(suppress_tokens) == 0:
+        suppress_tokens = []  # interpret empty string as an empty list
+    else:
+        assert isinstance(suppress_tokens, list), "suppress_tokens must be a list"
 
-    suppress_tokens = list(suppress_tokens)
-
-    # Ensure the following special tokens are suppressed when the user does
-    # not use the default set (-1).
     suppress_tokens.extend(
         [
             tokenizer.transcribe,
@@ -1214,7 +1259,7 @@ def get_suppressed_tokens(
         ]
     )
 
-    return sorted(set(suppress_tokens))
+    return tuple(sorted(set(suppress_tokens)))
 
 
 def merge_punctuations(alignment: List[dict], prepended: str, appended: str) -> None:
diff --git a/faster_whisper/utils.py b/faster_whisper/utils.py
index 93ade3a..481bd74 100644
--- a/faster_whisper/utils.py
+++ b/faster_whisper/utils.py
@@ -54,8 +54,9 @@ def download_model(
 
     Args:
       size_or_id: Size of the model to download from https://huggingface.co/Systran
-        (tiny, tiny.en, base, base.en, small, small.en medium, medium.en, large-v1, large-v2,
-        large-v3, large), or a CTranslate2-converted model ID from the Hugging Face Hub
+        (tiny, tiny.en, base, base.en, small, small.en, distil-small.en, medium, medium.en,
+        distil-medium.en, large-v1, large-v2, large-v3, large, distil-large-v2,
+        distil-large-v3), or a CTranslate2-converted model ID from the Hugging Face Hub
         (e.g. Systran/faster-whisper-large-v3).
       output_dir: Directory where the model should be saved. If not set, the model is saved in
         the cache directory.
diff --git a/faster_whisper/vad.py b/faster_whisper/vad.py
index 487dfa0..99dfb40 100644
--- a/faster_whisper/vad.py
+++ b/faster_whisper/vad.py
@@ -1,7 +1,6 @@
 import bisect
 import functools
 import os
-import warnings
 
 from typing import List, NamedTuple, Optional
 
@@ -25,9 +24,6 @@ class VadOptions(NamedTuple):
         split aggressively just before max_speech_duration_s.
       min_silence_duration_ms: In the end of each speech chunk wait for min_silence_duration_ms
         before separating it
-      window_size_samples: Audio chunks of window_size_samples size are fed to the silero VAD model.
-        WARNING! Silero VAD models were trained using 512, 1024, 1536 samples for 16000 sample rate.
-        Values other than these may affect model performance!!
       speech_pad_ms: Final speech chunks are padded by speech_pad_ms each side
     """
 
@@ -35,7 +31,6 @@ class VadOptions(NamedTuple):
     min_speech_duration_ms: int = 250
     max_speech_duration_s: float = float("inf")
     min_silence_duration_ms: int = 2000
-    window_size_samples: int = 1024
     speech_pad_ms: int = 400
 
 
@@ -61,15 +56,8 @@ def get_speech_timestamps(
     min_speech_duration_ms = vad_options.min_speech_duration_ms
     max_speech_duration_s = vad_options.max_speech_duration_s
     min_silence_duration_ms = vad_options.min_silence_duration_ms
-    window_size_samples = vad_options.window_size_samples
+    window_size_samples = 512
     speech_pad_ms = vad_options.speech_pad_ms
-
-    if window_size_samples not in [512, 1024, 1536]:
-        warnings.warn(
-            "Unusual window_size_samples! Supported window_size_samples:\n"
-            " - [512, 1024, 1536] for 16000 sampling_rate"
-        )
-
     sampling_rate = 16000
     min_speech_samples = sampling_rate * min_speech_duration_ms / 1000
     speech_pad_samples = sampling_rate * speech_pad_ms / 1000
@@ -84,14 +72,14 @@ def get_speech_timestamps(
     audio_length_samples = len(audio)
 
     model = get_vad_model()
-    state = model.get_initial_state(batch_size=1)
+    state, context = model.get_initial_states(batch_size=1)
 
     speech_probs = []
     for current_start_sample in range(0, audio_length_samples, window_size_samples):
         chunk = audio[current_start_sample : current_start_sample + window_size_samples]
         if len(chunk) < window_size_samples:
             chunk = np.pad(chunk, (0, int(window_size_samples - len(chunk))))
-        speech_prob, state = model(chunk, state, sampling_rate)
+        speech_prob, state, context = model(chunk, state, context, sampling_rate)
         speech_probs.append(speech_prob)
 
     triggered = False
@@ -261,12 +249,12 @@ class SileroVADModel:
             sess_options=opts,
         )
 
-    def get_initial_state(self, batch_size: int):
-        h = np.zeros((2, batch_size, 64), dtype=np.float32)
-        c = np.zeros((2, batch_size, 64), dtype=np.float32)
-        return h, c
+    def get_initial_states(self, batch_size: int):
+        state = np.zeros((2, batch_size, 128), dtype=np.float32)
+        context = np.zeros((batch_size, 64), dtype=np.float32)
+        return state, context
 
-    def __call__(self, x, state, sr: int):
+    def __call__(self, x, state, context, sr: int):
         if len(x.shape) == 1:
             x = np.expand_dims(x, 0)
         if len(x.shape) > 2:
@@ -276,16 +264,15 @@ class SileroVADModel:
         if sr / x.shape[1] > 31.25:
             raise ValueError("Input audio chunk is too short")
 
-        h, c = state
+        x = np.concatenate([context, x], axis=1)
 
         ort_inputs = {
             "input": x,
-            "h": h,
-            "c": c,
+            "state": state,
             "sr": np.array(sr, dtype="int64"),
         }
 
-        out, h, c = self.session.run(None, ort_inputs)
-        state = (h, c)
+        out, state = self.session.run(None, ort_inputs)
+        context = x[..., -64:]
 
-        return out, state
+        return out, state, context
diff --git a/faster_whisper/version.py b/faster_whisper/version.py
index 3b64d12..65eaef4 100644
--- a/faster_whisper/version.py
+++ b/faster_whisper/version.py
@@ -1,3 +1,3 @@
 """Version information."""
 
-__version__ = "1.0.1"
+__version__ = "1.0.3"
diff --git a/requirements.txt b/requirements.txt
index 1bbf0b0..b1497ab 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -1,5 +1,5 @@
-av==11.*
+av>=11.0,<13
 ctranslate2>=4.0,<5
 huggingface_hub>=0.13
-tokenizers>=0.13,<0.16
+tokenizers>=0.13,<1
 onnxruntime>=1.14,<2
diff --git a/tests/test_transcribe.py b/tests/test_transcribe.py
index d30a0fb..7fa27b1 100644
--- a/tests/test_transcribe.py
+++ b/tests/test_transcribe.py
@@ -1,6 +1,8 @@
 import os
 
 from faster_whisper import WhisperModel, decode_audio
+from faster_whisper.tokenizer import Tokenizer
+from faster_whisper.transcribe import get_suppressed_tokens
 
 
 def test_supported_languages():
@@ -97,3 +99,109 @@ def test_stereo_diarization(data_dir):
     segments, _ = model.transcribe(right)
     transcription = "".join(segment.text for segment in segments).strip()
     assert transcription == "The horizon seems extremely distant."
+
+
+def test_suppressed_tokens_minus_1():
+    model = WhisperModel("tiny.en")
+
+    tokenizer = Tokenizer(model.hf_tokenizer, False)
+    tokens = get_suppressed_tokens(tokenizer, [-1])
+    assert tokens == (
+        1,
+        2,
+        7,
+        8,
+        9,
+        10,
+        14,
+        25,
+        26,
+        27,
+        28,
+        29,
+        31,
+        58,
+        59,
+        60,
+        61,
+        62,
+        63,
+        90,
+        91,
+        92,
+        93,
+        357,
+        366,
+        438,
+        532,
+        685,
+        705,
+        796,
+        930,
+        1058,
+        1220,
+        1267,
+        1279,
+        1303,
+        1343,
+        1377,
+        1391,
+        1635,
+        1782,
+        1875,
+        2162,
+        2361,
+        2488,
+        3467,
+        4008,
+        4211,
+        4600,
+        4808,
+        5299,
+        5855,
+        6329,
+        7203,
+        9609,
+        9959,
+        10563,
+        10786,
+        11420,
+        11709,
+        11907,
+        13163,
+        13697,
+        13700,
+        14808,
+        15306,
+        16410,
+        16791,
+        17992,
+        19203,
+        19510,
+        20724,
+        22305,
+        22935,
+        27007,
+        30109,
+        30420,
+        33409,
+        34949,
+        40283,
+        40493,
+        40549,
+        47282,
+        49146,
+        50257,
+        50357,
+        50358,
+        50359,
+        50360,
+    )
+
+
+def test_suppressed_tokens_minus_value():
+    model = WhisperModel("tiny.en")
+
+    tokenizer = Tokenizer(model.hf_tokenizer, False)
+    tokens = get_suppressed_tokens(tokenizer, [13])
+    assert tokens == (13, 50257, 50357, 50358, 50359, 50360)