Automatic Speech Recognition
PEFT
TensorBoard
Safetensors
Chinese
wft
whisper
audio
speech
Generated from Trainer
Eval Results (legacy)
Instructions to use JacobLinCool/whisper-large-v3-turbo-common_voice_16_1-zh-TW-pissa with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use JacobLinCool/whisper-large-v3-turbo-common_voice_16_1-zh-TW-pissa with PEFT:
Task type is invalid.
- Notebooks
- Google Colab
- Kaggle
whisper-large-v3-turbo-common_voice_16_1-zh-TW-pissa / runs /Oct26_13-14-14_6a03c7a79a40 /events.out.tfevents.1729948928.6a03c7a79a40.338.0
- Xet hash:
- c79801fd952a7caa3c504d222458b2b847c663cd22aa295b54563442e92f7884
- Size of remote file:
- 4.31 MB
- SHA256:
- f5e3bb1eb48241cb19bcbf94016137f3a1616770215d1b6bde3244f4ad37bb45
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.