README.md

metadata

license: apache-2.0
tags:
  - generated_from_trainer
metrics:
  - wer
model-index:
  - name: openai/whisper-tiny
    results:
      - task:
          type: automatic-speech-recognition
          name: Automatic Speech Recognition
        dataset:
          name: rishabhjain16/infer_pfs
          type: rishabhjain16/infer_pfs
          config: en
          split: test
        metrics:
          - type: wer
            value: 42.3
            name: WER
      - task:
          type: automatic-speech-recognition
          name: Automatic Speech Recognition
        dataset:
          name: rishabhjain16/infer_myst
          type: rishabhjain16/infer_myst
          config: en
          split: test
        metrics:
          - type: wer
            value: 21.53
            name: WER
      - task:
          type: automatic-speech-recognition
          name: Automatic Speech Recognition
        dataset:
          name: rishabhjain16/cmu_wav
          type: rishabhjain16/cmu_wav
          config: en
          split: test
        metrics:
          - type: wer
            value: 27.6
            name: WER
      - task:
          type: automatic-speech-recognition
          name: Automatic Speech Recognition
        dataset:
          name: rishabhjain16/infer_cmu
          type: rishabhjain16/infer_cmu
          config: en
          split: test
        metrics:
          - type: wer
            value: 27.61
            name: WER
      - task:
          type: automatic-speech-recognition
          name: Automatic Speech Recognition
        dataset:
          name: rishabhjain16/libritts_dev_clean
          type: rishabhjain16/libritts_dev_clean
          config: en
          split: test
        metrics:
          - type: wer
            value: 17.92
            name: WER

openai/whisper-tiny

This model is a fine-tuned version of openai/whisper-tiny on the MyST(55 hours) dataset. It achieves the following results on the evaluation set (MyST 10 hours):

• Loss: 0.5675
• Wer: 20.2661

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: 64
• eval_batch_size: 32
• 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
0.3752	4.02	1000	0.4264	20.9318
0.2349	8.04	2000	0.4460	19.5872
0.095	13.01	3000	0.5086	20.6995
0.0416	17.02	4000	0.5504	20.7856
0.0339	21.04	5000	0.5675	20.2661

Framework versions

• Transformers 4.27.0.dev0
• Pytorch 1.13.1+cu117
• Datasets 2.9.1.dev0
• Tokenizers 0.13.2