Automatic Speech Recognition
Transformers
PyTorch
JAX
Tamil
whisper
whisper-event
Eval Results (legacy)
Instructions to use tamilnlpSLIIT/whisper-ta with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use tamilnlpSLIIT/whisper-ta with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="tamilnlpSLIIT/whisper-ta")# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("tamilnlpSLIIT/whisper-ta") model = AutoModelForSpeechSeq2Seq.from_pretrained("tamilnlpSLIIT/whisper-ta", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- 045c2a12f941d2f2d9a20cdb21f55945e1b497b32eaa237b52d491944babe81b
- Size of remote file:
- 3.06 GB
- SHA256:
- 6b2e39fe838e5664a31a0e79c4d094c79635c453641759ef50fd56b947a8907d
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.