Instructions to use MU-NLPC/whisper-small-audio-captioning with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use MU-NLPC/whisper-small-audio-captioning with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, WhisperForAudioCaptioning processor = AutoProcessor.from_pretrained("MU-NLPC/whisper-small-audio-captioning") model = WhisperForAudioCaptioning.from_pretrained("MU-NLPC/whisper-small-audio-captioning", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit History
-
Update model_class.py
Verified signaturea75f70c -
update model_class.py to be compatible with new transformers (transformers==4.36.2)
Verified signaturee8e231a
-
Update README.md
Verified signature92f63a6
-
Update README.md
Verified signaturebb611e0
-
Update model_class.py (#5)
Verified signature- Update model_class.py (c0a6c8d4ea3905485ea20f4f16f6a87c09538893) Co-authored-by: weilai <geekweilai@users.noreply.huggingface.co>53d0b79
-
Correct long-form generation config parameters 'max_initial_timestamp_index' and 'prev_sot_token_id'. (#4)
Verified signature- Correct long-form generation config parameters 'max_initial_timestamp_index' and 'prev_sot_token_id'. (b0cf192b828f589034f01108206a31aaa648d6fe) Co-authored-by: Patrick von Platen <patrickvonplaten@users.noreply.huggingface.co>e660e78
-
Update README.md
567801d -
Upload feature extractor (#3)
- Upload feature extractor (3392c8eff18459856d29fccd9b1c13356699880d)2b85fbf -
Upload tokenizer (#2)
- Upload tokenizer (b07840e09b3aec77c40b535c7d60a34200b2e817)a49f0c9 -
Upload WhisperForAudioCaptioning (#1)
- Upload WhisperForAudioCaptioning (4492e69fced7cb7d77bf972ea9a162b578410861)f4b7cce -
Create model_class.py
50b22ff -
Update README.md
a919c8f -
Update README.md
d2206a3 -
Update README.md
eac9c9c -
initial commit
857aba7