strip text on tsv and srt output

.dockerignore

@@ -0,0 +1 @@
+/venv

Dockerfile

@@ -1,7 +1,7 @@
 FROM docker.io/nvidia/cuda:12.0.0-cudnn8-runtime-ubuntu22.04
 
 RUN apt-get update && \
-    apt-get install -y ffmpeg python3 python3-pip && \
+    apt-get install -y ffmpeg python3 python3-pip git && \
     apt-get clean && \
     rm -rf /var/lib/apt/lists/*
 

requirements.txt

@@ -4,4 +4,5 @@ uvicorn[standard]
 whisper_ctranslate2
 opencc
 prometheus-fastapi-instrumentator
+git+https://git.yongyuancv.cn/heimoshuiyu/faster-whisper@prompt
 pydub

requirements_version.txt

@@ -1,48 +1,141 @@
-annotated-types==0.7.0
+aiohappyeyeballs==2.4.0
-anyio==4.4.0
+aiohttp==3.10.5
-av==12.2.0
+aiosignal==1.3.1
-certifi==2024.7.4
+alembic==1.13.2
-cffi==1.16.0
+annotated-types==0.7.0
-charset-normalizer==3.3.2
+antlr4-python3-runtime==4.9.3
-click==8.1.7
+anyio==4.4.0
-coloredlogs==15.0.1
+asteroid-filterbanks==0.4.0
-ctranslate2==4.3.1
+async-timeout==4.0.3
-fastapi==0.111.0
+attrs==24.2.0
-faster-whisper==1.0.3
+audioread==3.0.1
-filelock==3.15.4
+certifi==2024.8.30
-flatbuffers==24.3.25
+cffi==1.17.0
-fsspec==2024.6.1
+charset-normalizer==3.3.2
-h11==0.14.0
+click==8.1.7
-httptools==0.6.1
+coloredlogs==15.0.1
-huggingface-hub==0.23.4
+colorlog==6.8.2
-humanfriendly==10.0
+contourpy==1.3.0
-idna==3.7
+ctranslate2==4.3.1
-mpmath==1.3.0
+cycler==0.12.1
-numpy==1.26.4
+decorator==5.1.1
-onnxruntime==1.18.1
+docopt==0.6.2
-OpenCC==1.1.7
+einops==0.8.0
-packaging==24.1
+exceptiongroup==1.2.2
-prometheus-client==0.18.0
+fastapi==0.112.2
-prometheus-fastapi-instrumentator==7.0.0
+faster-whisper @ git+https://git.yongyuancv.cn/heimoshuiyu/faster-whisper@6e42088656e63c4222b8a193e8c783accb2a1df7
-protobuf==5.27.2
+filelock==3.15.4
-pycparser==2.22
+flatbuffers==24.3.25
-pydantic==2.8.2
+fonttools==4.53.1
-pydantic_core==2.20.1
+frozenlist==1.4.1
-pydub==0.25.1
+fsspec==2024.6.1
-python-dotenv==1.0.1
+greenlet==3.0.3
-python-multipart==0.0.9
+h11==0.14.0
-PyYAML==6.0.1
+httptools==0.6.1
-requests==2.32.3
+huggingface-hub==0.24.6
-sniffio==1.3.1
+humanfriendly==10.0
-sounddevice==0.4.7
+HyperPyYAML==1.2.2
-starlette==0.37.2
+idna==3.8
-sympy==1.12.1
+Jinja2==3.1.4
-tokenizers==0.19.1
+joblib==1.4.2
-tqdm==4.66.4
+julius==0.2.7
-typing_extensions==4.12.2
+kiwisolver==1.4.7
-urllib3==2.2.2
+lazy_loader==0.4
-uvicorn==0.30.1
+librosa==0.10.2.post1
-uvloop==0.19.0
+lightning==2.4.0
-watchfiles==0.22.0
+lightning-utilities==0.11.7
-websockets==12.0
+llvmlite==0.43.0
-whisper-ctranslate2==0.4.5
+Mako==1.3.5
+markdown-it-py==3.0.0
+MarkupSafe==2.1.5
+matplotlib==3.9.2
+mdurl==0.1.2
+mpmath==1.3.0
+msgpack==1.0.8
+multidict==6.0.5
+networkx==3.3
+numba==0.60.0
+numpy==1.26.4
+nvidia-cublas-cu12==12.1.3.1
+nvidia-cuda-cupti-cu12==12.1.105
+nvidia-cuda-nvrtc-cu12==12.1.105
+nvidia-cuda-runtime-cu12==12.1.105
+nvidia-cudnn-cu12==9.1.0.70
+nvidia-cufft-cu12==11.0.2.54
+nvidia-curand-cu12==10.3.2.106
+nvidia-cusolver-cu12==11.4.5.107
+nvidia-cusparse-cu12==12.1.0.106
+nvidia-nccl-cu12==2.20.5
+nvidia-nvjitlink-cu12==12.6.68
+nvidia-nvtx-cu12==12.1.105
+omegaconf==2.3.0
+onnxruntime==1.19.2
+OpenCC==1.1.9
+optuna==4.0.0
+packaging==24.1
+pandas==2.2.2
+pillow==10.4.0
+platformdirs==4.2.2
+pooch==1.8.2
+primePy==1.3
+prometheus-fastapi-instrumentator==7.0.0
+prometheus_client==0.20.0
+protobuf==5.28.0
+pyannote.audio==3.3.1
+pyannote.core==5.0.0
+pyannote.database==5.1.0
+pyannote.metrics==3.2.1
+pyannote.pipeline==3.0.1
+pycparser==2.22
+pydantic==2.8.2
+pydantic_core==2.20.1
+pydub==0.25.1
+Pygments==2.18.0
+pyparsing==3.1.4
+python-dateutil==2.9.0.post0
+python-dotenv==1.0.1
+python-multipart==0.0.9
+pytorch-lightning==2.4.0
+pytorch-metric-learning==2.6.0
+pytz==2024.1
+PyYAML==6.0.2
+requests==2.32.3
+rich==13.8.0
+ruamel.yaml==0.18.6
+ruamel.yaml.clib==0.2.8
+scikit-learn==1.5.1
+scipy==1.14.1
+semver==3.0.2
+sentencepiece==0.2.0
+shellingham==1.5.4
+six==1.16.0
+sniffio==1.3.1
+sortedcontainers==2.4.0
+sounddevice==0.5.0
+soundfile==0.12.1
+soxr==0.5.0.post1
+speechbrain==1.0.1
+SQLAlchemy==2.0.33
+starlette==0.38.4
+sympy==1.13.2
+tabulate==0.9.0
+tensorboardX==2.6.2.2
+threadpoolctl==3.5.0
+tokenizers==0.20.0
+torch==2.4.0
+torch-audiomentations==0.11.1
+torch-pitch-shift==1.2.4
+torchaudio==2.4.0
+torchmetrics==1.4.1
+tqdm==4.66.5
+triton==3.0.0
+typer==0.12.5
+typing_extensions==4.12.2
+tzdata==2024.1
+urllib3==2.2.2
+uvicorn==0.30.6
+uvloop==0.20.0
+watchfiles==0.24.0
+websockets==13.0.1
+whisper-ctranslate2==0.4.5
+yarl==1.9.8

start-podman.sh

@@ -0,0 +1,11 @@
+#!/bin/bash
+
+podman run -d --name whisper-fastapi \
+    --restart unless-stopped \
+    --name whisper-fastapi \
+    -v ~/.cache/huggingface:/root/.cache/huggingface \
+    --device nvidia.com/gpu=all --security-opt=label=disable \
+    --gpus all \
+    -p 5000:5000 \
+    docker.io/heimoshuiyu/whisper-fastapi:latest \
+    --model large-v2

whisper_fastapi.py

@@ -78,7 +78,7 @@ def tsv_writer(generator: Generator[dict[str, Any], Any, None]):
     for i, segment in enumerate(generator):
         start_time = str(round(1000 * segment["start"]))
         end_time = str(round(1000 * segment["end"]))
-        text = segment["text"]
+        text = segment["text"].strip()
         yield f"{start_time}\t{end_time}\t{text}\n"
 
 
@@ -90,7 +90,7 @@ def srt_writer(generator: Generator[dict[str, Any], Any, None]):
         end_time = format_timestamp(
             segment["end"], decimal_marker=",", always_include_hours=True
         )
-        text = segment["text"]
+        text = segment["text"].strip()
         yield f"{i}\n{start_time} --> {end_time}\n{text}\n\n"
 
 
@@ -99,7 +99,7 @@ def vtt_writer(generator: Generator[dict[str, Any], Any, None]):
     for i, segment in enumerate(generator):
         start_time = format_timestamp(segment["start"])
         end_time = format_timestamp(segment["end"])
-        text = segment["text"]
+        text = segment["text"].strip()
         yield f"{start_time} --> {end_time}\n{text}\n\n"
 
 
@@ -159,6 +159,8 @@ def stream_builder(
 
 @app.websocket("/k6nele/status")
 @app.websocket("/konele/status")
+@app.websocket("/v1/k6nele/status")
+@app.websocket("/v1/konele/status")
 async def konele_status(
     websocket: WebSocket,
 ):
@@ -169,6 +171,8 @@ async def konele_status(
 
 @app.websocket("/k6nele/ws")
 @app.websocket("/konele/ws")
+@app.websocket("/v1/k6nele/ws")
+@app.websocket("/v1/konele/ws")
 async def konele_ws(
     websocket: WebSocket,
     task: Literal["transcribe", "translate"] = "transcribe",
@@ -233,6 +237,8 @@ async def konele_ws(
 
 @app.post("/k6nele/post")
 @app.post("/konele/post")
+@app.post("/v1/k6nele/post")
+@app.post("/v1/konele/post")
 async def translateapi(
     request: Request,
     task: Literal["transcribe", "translate"] = "transcribe",