Whisper Telugu Medium
This model is a fine-tuned version of openai/whisper-medium on the Telugu data available from multiple publicly available ASR corpuses. It has been fine-tuned as a part of the Whisper fine-tuning sprint.
Training and evaluation data at Speech Lab, IITM
Training Data: CSTD IIIT-H ASR Corpus, ULCA ASR Corpus, Shrutilipi ASR Corpus, Microsoft Research Telugu Corpus (Train+Dev), Babel ASR Corpus, Google/Fleurs (Train+Dev) set. Evaluation Data: Babel Test, Microsoft Research Telugu Corpus Test, Google/Fleurs Test set, OpenSLR.
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 24
- eval_batch_size: 48
- seed: 22
- optimizer: adamw_bnb_8bit
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 15000
- training_steps: 13752 (terminated upon convergence. Initially set to 89520 steps)
- mixed_precision_training: True
Acknowledgement
This work was done at Speech Lab, IITM. The compute resources for this work were funded by "Bhashini: National Language translation Mission" project of the Ministry of Electronics and Information Technology (MeitY), Government of India.