README.md

metadata

language:
  - te
license: apache-2.0
base_model: openai/whisper-medium
tags:
  - hf-asr-leaderboard
  - generated_from_trainer
datasets:
  - Sonal0205/telugu_asr
metrics:
  - wer
model-index:
  - name: Whisper Medium te - telugu
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: Telugu ASR
          type: Sonal0205/telugu_asr
          args: 'config: te, split: test'
        metrics:
          - name: Wer
            type: wer
            value: 39.00118906064209

Whisper Medium te - telugu

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

• Loss: 0.1044
• Wer: 39.0012

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: 16
• eval_batch_size: 8
• 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: 4000

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0415	2.1142	1000	0.0918	57.5208
0.0104	4.2283	2000	0.0984	38.3769
0.0023	6.3425	3000	0.1018	31.8074
0.0001	8.4567	4000	0.1044	39.0012

Framework versions

• Transformers 4.42.0.dev0
• Pytorch 2.4.0.dev20240527+cu118
• Datasets 2.19.1
• Tokenizers 0.19.1