Instructions to use tensorops/whisper-small-th with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use tensorops/whisper-small-th with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="tensorops/whisper-small-th")# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("tensorops/whisper-small-th") model = AutoModelForSpeechSeq2Seq.from_pretrained("tensorops/whisper-small-th", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- 7f3a71367b4a49840d49dd892114e8b8398b112af56830135435581e1c26a8bf
- Size of remote file:
- 967 MB
- SHA256:
- deaf8849f62e9ce97bb18ddcd9801850f29b84d73b99edeaab9d210f88853c8e
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.