README.md

metadata

license: apache-2.0
base_model: openai/whisper-small
tags:
  - generated_from_trainer
datasets:
  - common_voice_11_0
metrics:
  - wer
model-index:
  - name: whisper-small-rw
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: common_voice_11_0
          type: common_voice_11_0
          config: rw
          split: None
          args: rw
        metrics:
          - name: Wer
            type: wer
            value: 68.72705657437083

whisper-small-rw

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: 0.9918
• Wer: 68.7271

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
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.6952	1.0	1000	0.9920	70.5023
0.4771	2.0	2000	0.9260	68.3624
0.3132	3.0	3000	0.9506	68.0732
0.2025	4.0	4000	0.9918	68.7271

Framework versions

• Transformers 4.40.0
• Pytorch 2.1.0+cu121
• Datasets 2.19.0
• Tokenizers 0.19.1