Hugging Face's logo

CKSINGH
/
whisper-small-hi-iiib

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
Safetensors
Hindi
whisper
hf-asr-leaderboard
Generated from Trainer
Model card Files Metrics Community
whisper-small-hi-iiib / README.md
CKSINGH's picture
CKSINGH
End of training
9c3cffd
preview code
|
raw
history blame contribute delete
1.76 kB
metadata
language:
  - hi
license: apache-2.0
base_model: openai/whisper-medium
tags:
  - hf-asr-leaderboard
  - generated_from_trainer
metrics:
  - wer
model-index:
  - name: Whisper small Hi - CKS 1311 iiitb
    results: []

Whisper small Hi - CKS 1311 iiitb

This model is a fine-tuned version of openai/whisper-medium on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.1203
  • Wer: 10.8852
  • Cer: 3.4179

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: 1.75e-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: 2000
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer Cer
0.0291 8.77 500 0.1099 14.2344 4.1970
0.004 17.54 1000 0.1114 10.8852 3.4682
0.0001 26.32 1500 0.1185 10.7656 3.3677
0.0 35.09 2000 0.1203 10.8852 3.4179

Framework versions

  • Transformers 4.36.0.dev0
  • Pytorch 2.1.0+cu118
  • Datasets 2.14.6
  • Tokenizers 0.14.1