Hugging Face's logo

singhajeet13
/
whisper-hindi-ASR-STT

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Hindi
whisper
hf-asr-leaderboard
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
whisper-hindi-ASR-STT / README.md
singhajeet13's picture
singhajeet13
End of training
c931f23 verified
preview code
|
raw
history blame contribute delete
1.67 kB
metadata
language:
  - hi
license: apache-2.0
base_model: openai/whisper-small
tags:
  - hf-asr-leaderboard
  - generated_from_trainer
metrics:
  - wer
model-index:
  - name: Whisper Small Hindi ASR
    results: []

Whisper Small Hindi ASR

This model is a fine-tuned version of openai/whisper-small on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set:

  • Loss: 1.7739
  • Wer: 70.9346

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: 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: 40
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer
2.1089 0.01 10 2.2857 86.8958
2.1456 0.01 20 2.2165 85.6048
2.1244 0.02 30 2.0245 80.2675
1.6134 0.02 40 1.7739 70.9346

Framework versions

  • Transformers 4.37.2
  • Pytorch 2.1.0+cu121
  • Datasets 2.16.1
  • Tokenizers 0.15.1