Instructions to use drepic/whisper-small-jp with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use drepic/whisper-small-jp with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="drepic/whisper-small-jp")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("drepic/whisper-small-jp") model = AutoModelForSpeechSeq2Seq.from_pretrained("drepic/whisper-small-jp", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download accelerate_state/optimizer.bin from drepic/whisper-small-jp: direct link, hf CLI and curl.
- Browser
- Download file 28.6 MB
-
https://huggingface.co/drepic/whisper-small-jp/resolve/main/accelerate_state/optimizer.bin
- Command line
-
hf download hf://drepic/whisper-small-jp/accelerate_state/optimizer.bin
-
curl -L -o optimizer.bin https://huggingface.co/drepic/whisper-small-jp/resolve/main/accelerate_state/optimizer.bin
28.6 MB
- Xet hash:
- e1c5b9d5b61096c9865e13e400320f2cb67d9110a50d1973a5945945100516d0
- Size of remote file:
- 28.6 MB
- SHA256:
- e1bca8c1380bd900535353634e8414f975810c2fb101da542b848619bceb6e05
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.