README.md

metadata

language:
  - hi
license: apache-2.0
tags:
  - generated_from_trainer
base_model: Aakali/whisper-medium-hi
datasets:
  - mozilla-foundation/common_voice_11_0
metrics:
  - wer
model-index:
  - name: Whisper medium-translate Hi - Aa
    results:
      - task:
          type: automatic-speech-recognition
          name: Automatic Speech Recognition
        dataset:
          name: Common Voice 11.0
          type: mozilla-foundation/common_voice_11_0
          args: 'config: hi, split: test'
        metrics:
          - type: wer
            value: 48.11612382957753
            name: Wer

Whisper medium-translate Hi - Aa

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

• Loss: 0.9904
• Wer: 48.1161

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: 500
• training_steps: 5000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.1405	2.4450	1000	0.7580	51.5075
0.0245	4.8900	2000	0.8571	51.4000
0.0026	7.3350	3000	0.9280	48.3132
0.0011	9.7800	4000	0.9673	47.6457
0.0006	12.2249	5000	0.9904	48.1161

Framework versions

• Transformers 4.41.0
• Pytorch 2.2.1+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1