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

Add large-v1 model

Browse Source
This commit is contained in:
Guillaume Klein
2023-03-28 14:36:10 +02:00
parent 8246479fda
commit 0224400584
2 changed files with 3 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
faster_whisper/transcribe.py
View File

@@ -69,7 +69,7 @@ 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, or large-v2) or a path to a converted small, small.en, medium, medium.en, large-v1, or large-v2) or a path to a converted
model directory. When a size is configured, the converted model is downloaded model directory. When a size is configured, the converted model is downloaded
from the Hugging Face Hub. from the Hugging Face Hub.
device: Device to use for computation ("cpu", "cuda", "auto"). device: Device to use for computation ("cpu", "cuda", "auto").

3
faster_whisper/utils.py
View File

@@ -13,6 +13,7 @@ _MODELS = (
"small", "small",
"medium.en", "medium.en",
"medium", "medium",
"large-v1",
"large-v2", "large-v2",
) )
@@ -28,7 +29,7 @@ def download_model(
Args: Args:
size: Size of the model to download (tiny, tiny.en, base, base.en, small, small.en, size: Size of the model to download (tiny, tiny.en, base, base.en, small, small.en,
medium, medium.en, or large-v2). medium, medium.en, large-v1, or 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 standard Hugging Face cache directory. the standard Hugging Face cache directory.
show_progress_bars: Show the tqdm progress bars during the download. show_progress_bars: Show the tqdm progress bars during the download.