README.md

metadata

license: apache-2.0
base_model: openai/whisper-tiny
tags:
  - generated_from_trainer
datasets:
  - dataset_whisper
metrics:
  - wer
model-index:
  - name: Transcriber-Medium
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: dataset_whisper
          type: dataset_whisper
          config: default
          split: test
          args: default
        metrics:
          - name: Wer
            type: wer
            value: 108.52032520325203

Transcriber-Medium

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

• Loss: 2.9360
• Wer: 108.5203

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: 2
• eval_batch_size: 2
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 16
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 200
• training_steps: 100

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
2.7536	4.02	100	2.9360	108.5203

Framework versions

• Transformers 4.32.0.dev0
• Pytorch 1.12.1+cu113
• Datasets 2.14.1
• Tokenizers 0.13.3