Hugging Face's logo

CKSINGH
/
whisper-small-hi-firefox

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
Safetensors
Hindi
whisper
hf-asr-leaderboard
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
whisper-small-hi-firefox / README.md
CKSINGH's picture
CKSINGH
End of training
bc63089
preview code
|
raw history blame
No virus
1.63 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 1611 firefox
    results: []

Whisper small Hi - CKS 1611 firefox

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: 0.4267
  • Wer: 36.8876
  • Cer: 14.1067

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: 1
  • training_steps: 2
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer Cer
0.0159 0.14 1 0.4178 37.2719 14.0530
0.0623 0.29 2 0.4267 36.8876 14.1067

Framework versions

  • Transformers 4.36.0.dev0
  • Pytorch 2.1.0+cu118
  • Datasets 2.14.7
  • Tokenizers 0.15.0