README.md

metadata

language:
  - dv
license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - mozilla-foundation/common_voice_13_0
metrics:
  - wer
base_model: openai/whisper-small
model-index:
  - name: Whisper Small Dv - Sanchit Gandhi
    results:
      - task:
          type: automatic-speech-recognition
          name: Automatic Speech Recognition
        dataset:
          name: Common Voice 13
          type: mozilla-foundation/common_voice_13_0
          config: dv
          split: test
          args: dv
        metrics:
          - type: wer
            value: 10.833883923914177
            name: Wer

Whisper Small Dv - Sanchit Gandhi

This model is a fine-tuned version of openai/whisper-small on the Common Voice 13 dataset. It achieves the following results on the evaluation set:

• Loss: 0.3057
• Wer Ortho: 56.5986
• Wer: 10.8339

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: 4000

Training results

Training Loss	Epoch	Step	Validation Loss	Wer Ortho	Wer
0.0657	3.26	1000	0.1608	58.2144	11.9727
0.0117	6.51	2000	0.2264	58.2213	11.2060
0.0014	9.77	3000	0.2866	57.3438	11.1069
0.0002	13.03	4000	0.3057	56.5986	10.8339

Framework versions

• Transformers 4.31.0.dev0
• Pytorch 2.0.1+cu118
• Datasets 2.13.1.dev0
• Tokenizers 0.13.3