README.md

metadata

language:
  - hi
license: apache-2.0
tags:
  - whisper-event
metrics:
  - wer
model-index:
  - name: Whisper Hindi Small - Vasista Sai Lodagala
    results:
      - task:
          type: automatic-speech-recognition
          name: Automatic Speech Recognition
        dataset:
          name: google/fleurs
          type: google/fleurs
          config: hi_in
          split: test
        metrics:
          - type: wer
            value: 9.02
            name: WER
      - task:
          type: automatic-speech-recognition
          name: Automatic Speech Recognition
        dataset:
          name: mozilla-foundation/common_voice_11_0
          type: mozilla-foundation/common_voice_11_0
          config: hi
          split: test
        metrics:
          - type: wer
            value: 14.12
            name: WER

Whisper Hindi Small

This model is a fine-tuned version of openai/whisper-small on the Hindi 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: GramVaani ASR Corpus, ULCA ASR Corpus, Shrutilipi ASR Corpus, Google/Fleurs (Train+Dev) set.

Evaluation Data: GramVaani ASR Corpus Test, Google/Fleurs Test set.

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 1.75e-05
• train_batch_size: 48
• eval_batch_size: 32
• seed: 22
• optimizer: adamw_bnb_8bit
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 20000
• training_steps: 19377 (Initially set to 129180 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.