README.md

metadata

license: apache-2.0
base_model: openai/whisper-tiny
tags:
  - generated_from_trainer
datasets:
  - common_voice_13_0
metrics:
  - wer
model-index:
  - name: whisper_tiny_cs
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: common_voice_13_0
          type: common_voice_13_0
          config: cs
          split: test
          args: cs
        metrics:
          - name: Wer
            type: wer
            value: 53.0400387724153

whisper_tiny_cs

This model is a fine-tuned version of openai/whisper-tiny on the common_voice_13_0 dataset. It achieves the following results on the evaluation set:

• Loss: 0.6426
• Wer: 53.0400

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: 32
• eval_batch_size: 8
• seed: 42
• distributed_type: multi-GPU
• num_devices: 2
• gradient_accumulation_steps: 4
• total_train_batch_size: 256
• total_eval_batch_size: 16
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 1000
• training_steps: 300

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.8297	1.45	100	0.8730	66.3524
0.62	2.91	200	0.7188	57.8663
0.4986	4.36	300	0.6426	53.0400

Framework versions

• Transformers 4.31.0
• Pytorch 2.0.1+cu117
• Datasets 2.14.4
• Tokenizers 0.13.3