heimoshuiyu/faster-whisper
1
0
Fork 0
Code Issues Pull Requests 1 Packages Projects Releases Wiki Activity

Add "large" alias for "large-v2" model (#453)

Browse Source
This commit is contained in:
Guillaume Klein
2023-09-04 11:54:42 +02:00
committed by GitHub
parent f0ff12965a
commit 1e6eb967c9
2 changed files with 21 additions and 22 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
faster_whisper/transcribe.py
View File

@@ -92,7 +92,7 @@ class WhisperModel:
Args: Args:
model_size_or_path: Size of the model to use (tiny, tiny.en, base, base.en, model_size_or_path: Size of the model to use (tiny, tiny.en, base, base.en,
small, small.en, medium, medium.en, large-v1, or large-v2), a path to a converted small, small.en, medium, medium.en, large-v1, large-v2, or large), a path to a converted
model directory, or a CTranslate2-converted Whisper model ID from the Hugging Face Hub. model directory, or a CTranslate2-converted Whisper model ID from the Hugging Face Hub.
When a size or a model ID is configured, the converted model is downloaded When a size or a model ID is configured, the converted model is downloaded
from the Hugging Face Hub. from the Hugging Face Hub.

41
faster_whisper/utils.py
View File

@@ -9,18 +9,19 @@ import requests
from tqdm.auto import tqdm from tqdm.auto import tqdm
_MODELS = ( _MODELS = {
"tiny.en", "tiny.en": "guillaumekln/faster-whisper-tiny.en",
"tiny", "tiny": "guillaumekln/faster-whisper-tiny",
"base.en", "base.en": "guillaumekln/faster-whisper-base.en",
"base", "base": "guillaumekln/faster-whisper-base",
"small.en", "small.en": "guillaumekln/faster-whisper-small.en",
"small", "small": "guillaumekln/faster-whisper-small",
"medium.en", "medium.en": "guillaumekln/faster-whisper-medium.en",
"medium", "medium": "guillaumekln/faster-whisper-medium",
"large-v1", "large-v1": "guillaumekln/faster-whisper-large-v1",
"large-v2", "large-v2": "guillaumekln/faster-whisper-large-v2",
) "large": "guillaumekln/faster-whisper-large-v2",
}
def get_assets_path(): def get_assets_path():
@@ -41,12 +42,11 @@ def download_model(
): ):
"""Downloads a CTranslate2 Whisper model from the Hugging Face Hub. """Downloads a CTranslate2 Whisper model from the Hugging Face Hub.
The model is downloaded from https://huggingface.co/guillaumekln.
Args: Args:
size_or_id: Size of the model to download (tiny, tiny.en, base, base.en, small, small.en, size_or_id: Size of the model to download from https://huggingface.co/guillaumekln
medium, medium.en, large-v1, or large-v2), or a CTranslate2-converted model ID (tiny, tiny.en, base, base.en, small, small.en medium, medium.en, large-v1, large-v2,
from the Hugging Face Hub (e.g. guillaumekln/faster-whisper-large-v2). large), or a CTranslate2-converted model ID from the Hugging Face Hub
(e.g. guillaumekln/faster-whisper-large-v2).
output_dir: Directory where the model should be saved. If not set, the model is saved in output_dir: Directory where the model should be saved. If not set, the model is saved in
the cache directory. the cache directory.
local_files_only: If True, avoid downloading the file and return the path to the local local_files_only: If True, avoid downloading the file and return the path to the local
@@ -62,14 +62,13 @@ def download_model(
if re.match(r".*/.*", size_or_id): if re.match(r".*/.*", size_or_id):
repo_id = size_or_id repo_id = size_or_id
else: else:
if size_or_id not in _MODELS: repo_id = _MODELS.get(size_or_id)
if repo_id is None:
raise ValueError( raise ValueError(
"Invalid model size '%s', expected one of: %s" "Invalid model size '%s', expected one of: %s"
% (size_or_id, ", ".join(_MODELS)) % (size_or_id, ", ".join(_MODELS.keys()))
) )
repo_id = "guillaumekln/faster-whisper-%s" % size_or_id
allow_patterns = [ allow_patterns = [
"config.json", "config.json",
"model.bin", "model.bin",