Automatic Speech Recognition
Transformers
PyTorch
whisper
Generated from Trainer
Eval Results (legacy)
Instructions to use kimjaewon/whisper-tiny-us with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use kimjaewon/whisper-tiny-us with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="kimjaewon/whisper-tiny-us")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("kimjaewon/whisper-tiny-us") model = AutoModelForSpeechSeq2Seq.from_pretrained("kimjaewon/whisper-tiny-us", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download pytorch_model.bin from kimjaewon/whisper-tiny-us: direct link, hf CLI and curl.
- Browser
- Download file 151 MB
-
https://huggingface.co/kimjaewon/whisper-tiny-us/resolve/main/pytorch_model.bin
- Command line
-
hf download hf://kimjaewon/whisper-tiny-us/pytorch_model.bin
-
curl -L -o pytorch_model.bin https://huggingface.co/kimjaewon/whisper-tiny-us/resolve/main/pytorch_model.bin
151 MB
- Xet hash:
- dc975dcade346e5cd077e898fd4c95aba018d76913a8478cbc2bfc856403db74
- Size of remote file:
- 151 MB
- SHA256:
- 85134b242ddae699e93b4c8c53e56500c2f622391839fdc2d5da0246fd925724
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.