Hugging Face's logo

harupurito
/
whisper-small-mar

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Marathi
whisper
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
whisper-small-mar / README.md
harupurito's picture
harupurito
End of training
0701fac verified
preview code
|
raw
history blame contribute delete
1.68 kB
metadata
language:
  - mar
license: apache-2.0
base_model: openai/whisper-small
tags:
  - generated_from_trainer
metrics:
  - wer
model-index:
  - name: Whisper Small Mar - Harpreet Singh Anand
    results: []

Whisper Small Mar - Harpreet Singh Anand

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

  • Loss: 0.1644
  • Wer: 14.3917

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
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer
0.0018 12.66 1000 0.1550 16.6181
0.0001 25.32 2000 0.1529 14.6303
0.0 37.97 3000 0.1617 14.4977
0.0 50.63 4000 0.1644 14.3917

Framework versions

  • Transformers 4.39.2
  • Pytorch 2.1.1+cu121
  • Datasets 2.18.0
  • Tokenizers 0.15.2