Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
whisper
Generated from Trainer
Eval Results (legacy)
Instructions to use taohoang/whisper-tiny-en-US with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use taohoang/whisper-tiny-en-US with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="taohoang/whisper-tiny-en-US")# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("taohoang/whisper-tiny-en-US") model = AutoModelForSpeechSeq2Seq.from_pretrained("taohoang/whisper-tiny-en-US", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- adaea51f3c3c8ef80d503a6f7cc2b1c7fd8745c85695bbc6aa09c7cb88ab704a
- Size of remote file:
- 4.09 kB
- SHA256:
- 238a170ff09bfaa5789374c4e5fff49ba2dbbd08ea8c00229be7c286b8d05431
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.