callbacks = [EarlyStoppingCallback(early_stopping_patience=3)]
- https://colab.research.google.com/drive/1P4ClLkPmfsaKn2tBbRp0nVjGMRKR-EWz
- https://huggingface.co/blog/fine-tune-whisper#combine-to-create-a-whisperprocessor
- https://medium.com/grabngoinfo/transfer-learning-for-text-classification-using-hugging-face-transformers-trainer-13407187cf89 https://github.com/huggingface/transformers/tree/main/examples/pytorch/speech-recognition#warm-started-speech-encoder-decoder-model huggingface/community-events#100
https://huggingface.co/spaces/openai/whisper/discussions/6 https://github.com/huggingface/community-events/tree/main/whisper-fine-tuning-event#recommended-training-configurations
https://github.com/krylm/whisper-event-tuning https://huggingface.co/blog/fine-tune-whisper
https://huggingface.co/blog/fine-tune-whisper#training-and-evaluation
https://towardsdatascience.com/speech-to-text-with-openais-whisper-53d5cea9005e
ssh -L 8096:127.0.0.1:8096 -N -f gaurisht@cleopatra.ijs.si
https://www.machinelearningnuggets.com/gradio-tutorial/ V1 whisper-small-gom-LDC-v1.0
KonkaniCorpusDatasetRestructuredNonRepeating.csv - audio and sentence as it is KonkaniCorpusDatasetRestructuredRepeatingRemoved.csv repeating values removed |gom-LDC-v1.non-repeating" KonkaniCorpusDatasetRestructuredNonRepeating ./{model_name}-gom-LDC-v1.3-repeating-not fixed
CIIL dataset