Introduce Whisper large-v3-turbo into faster-whisper
All you have to do is just follow the hints discussed in the issue below:
- Fetch the model into the local
from huggingface_hub import snapshot_download repo_id = "deepdml/faster-whisper-large-v3-turbo-ct2" local_dir = "faster-whisper-large-v3-turbo-ct2" snapshot_download(repo_id=repo_id, local_dir=local_dir, repo_type="model")
- Specify
faster-whisper-large-v3-turbo-ct2
when creating WhisperModel
from faster_whisper import WhisperModel model = WhisperModel("faster-whisper-large-v3-turbo-ct2")
Introduce Whisper large-v3-turbo into whisper_streaming
- Add
faster-whisper-large-v3-turbo-ct2
into the choise set of --model argument
parser.add_argument('--model', type=str, default='large-v2', choices="tiny.en,tiny,base.en,base,small.en,small,medium.en,medium,large-v1,large-v2,large-v3,large,faster-whisper-large-v3-turbo-ct2".split(","),help="Name size of the Whisper model to use (default: large-v2). The model is automatically downloaded from the model hub if not present in model cache dir.")
- Specify
faster-whisper-large-v3-turbo-ct2
as the model when calling whisper_online_server.py
python whisper_online_server.py --model faster-whisper-large-v3-turbo-ct2 --backend faster-whisper # and so on