README.md

metadata

library_name: transformers
language:
  - hi
license: apache-2.0
base_model: openai/whisper-small
tags:
  - generated_from_trainer
datasets:
  - mozilla-foundation/common_voice_11_0
metrics:
  - wer
model-index:
  - name: Whisper Small Hi - Sanchit Gandhi
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: Common Voice 11.0
          type: mozilla-foundation/common_voice_11_0
          args: 'config: hi, split: test'
        metrics:
          - name: Wer
            type: wer
            value: 47.02479338842976

Whisper Small Hi - Sanchit Gandhi

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

• Loss: 0.5644
• Wer: 47.0248

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: 4
• eval_batch_size: 8
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 50
• training_steps: 1700
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.5424	0.4854	100	0.6264	65.1653
0.4626	0.9709	200	0.5054	56.4463
0.2254	1.4563	300	0.4883	57.9752
0.1756	1.9417	400	0.4684	52.7273
0.0827	2.4272	500	0.4958	52.1901
0.0579	2.9126	600	0.4807	50.9091
0.0233	3.3981	700	0.5169	50.5372
0.0175	3.8835	800	0.5269	49.1736
0.0061	4.3689	900	0.5338	47.8099
0.007	4.8544	1000	0.5347	50.0
0.0021	5.3398	1100	0.5416	47.8926
0.0034	5.8252	1200	0.5490	49.2562
0.0014	6.3107	1300	0.5583	47.7686
0.0011	6.7961	1400	0.5583	47.0661
0.001	7.2816	1500	0.5605	46.9008
0.0008	7.7670	1600	0.5632	47.0248
0.0008	8.2524	1700	0.5644	47.0248

Framework versions

• Transformers 4.53.2
• Pytorch 2.7.1+cu118
• Datasets 4.0.0
• Tokenizers 0.21.2