README.md

metadata

license: apache-2.0
base_model: openai/whisper-small
tags:
  - generated_from_trainer
datasets:
  - generator
metrics:
  - wer
model-index:
  - name: ASR-whisper-small-1
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: generator
          type: generator
          config: default
          split: train
          args: default
        metrics:
          - name: Wer
            type: wer
            value: 0.49970056294166965

ASR-whisper-small-1

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

• Loss: 0.9304
• Wer: 0.4997

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: 0.0005
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 700
• training_steps: 3000

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
1.6949	0.33	1000	1.6964	0.9265
0.9422	1.31	2000	1.1670	0.7292
0.4947	2.28	3000	0.9304	0.4997

Framework versions

• Transformers 4.31.0
• Pytorch 2.0.0
• Datasets 2.14.4
• Tokenizers 0.13.3