README.md

metadata

language:
  - te
license: apache-2.0
tags:
  - hf-asr-leaderboard
  - generated_from_trainer
datasets:
  - Chai_Bisket_Stories_16-08-2021_14-17
metrics:
  - wer
model-index:
  - name: Whisper Small Telugu - Naga Budigam
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: Chai_Bisket_Stories_16-08-2021_14-17
          type: Chai_Bisket_Stories_16-08-2021_14-17
          args: 'config: te, split: test'
        metrics:
          - name: Wer
            type: wer
            value: 307.8748651564186

Whisper Small Telugu - Naga Budigam

This model is a fine-tuned version of openai/whisper-small on the Chai_Bisket_Stories_16-08-2021_14-17 dataset. It achieves the following results on the evaluation set:

• Loss: 1.1913
• Wer: 307.8749

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: 4
• eval_batch_size: 2
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 50
• training_steps: 400
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
1.4863	0.97	100	1.4943	283.3873
1.2696	1.94	200	1.3335	280.5825
1.1176	2.91	300	1.2336	312.1899
1.0132	3.88	400	1.1913	307.8749

Framework versions

• Transformers 4.25.0.dev0
• Pytorch 1.12.1+cu113
• Datasets 2.7.1
• Tokenizers 0.13.2