README.md

metadata

language:
  - hi
license: apache-2.0
base_model: openai/whisper-large
tags:
  - hf-asr-leaderboard
  - speech-recognition
  - whisper
  - hindi
  - generated_from_trainer
datasets:
  - mozilla-foundation/common_voice_11_0
metrics:
  - wer
model-index:
  - name: whisper-small-hindi
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: Common Voice 11.0
          type: mozilla-foundation/common_voice_11_0
          config: hi
          split: None
          args: 'config: hi, split: test'
        metrics:
          - name: Wer
            type: wer
            value: 34.055701345974775

whisper-small-hindi

This model is a fine-tuned version of openai/whisper-large on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set:

• Loss: 0.2842
• Wer: 34.0557

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 1e-05
• train_batch_size: 16
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 100
• training_steps: 818
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.1263	1.0	409	0.2835	36.1212
0.0693	2.0	818	0.2842	34.0557

Framework versions

• Transformers 4.42.4
• Pytorch 2.3.1+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1