Hugging Face's logo

makhataei
/
Whisper-Small-Common-Voice

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Persian
whisper
fa-asr
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
Whisper-Small-Common-Voice / README.md
makhataei's picture
makhataei
End of training
23cfbe5
preview code
|
raw
history blame
3.37 kB
metadata
language:
  - fa
license: apache-2.0
base_model: makhataei/Whisper-Small-Common-Voice
tags:
  - fa-asr
  - generated_from_trainer
datasets:
  - mozilla-foundation/common_voice_16_0
metrics:
  - wer
model-index:
  - name: Whisper Small Persian
    results: []

Whisper Small Persian

This model is a fine-tuned version of makhataei/Whisper-Small-Common-Voice on the Common Voice 16.0 dataset. It achieves the following results on the evaluation set:

  • Loss: 0.7811
  • Wer: 43.9230

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-06
  • train_batch_size: 10
  • eval_batch_size: 10
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 40
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 50
  • training_steps: 3000

Training results

Training Loss Epoch Step Validation Loss Wer
0.0014 0.16 100 0.7112 43.9740
0.0048 0.31 200 0.7077 42.5968
0.0048 0.47 300 0.7099 42.8982
0.0032 0.62 400 0.7116 43.4802
0.0041 0.78 500 0.7156 43.6935
0.0025 0.93 600 0.7184 43.5660
0.0012 1.09 700 0.7212 44.5421
0.0005 1.25 800 0.7338 43.8164
0.0014 1.4 900 0.7409 44.0529
0.0009 1.56 1000 0.7414 44.3010
0.001 1.71 1100 0.7408 45.0475
0.0006 1.87 1200 0.7447 44.6812
0.0005 2.03 1300 0.7493 43.4268
0.0005 2.18 1400 0.7564 43.2877
0.0004 2.34 1500 0.7580 43.8280
0.0004 2.49 1600 0.7626 43.5173
0.019 2.65 1700 0.7654 43.7677
0.0004 2.8 1800 0.7679 43.8001
0.0003 2.96 1900 0.7694 43.7491
0.0003 3.12 2000 0.7713 43.8906
0.0003 3.27 2100 0.7737 43.7978
0.0003 3.43 2200 0.7763 43.6031
0.0003 3.58 2300 0.7770 43.9253
0.0003 3.74 2400 0.7778 43.9995
0.0003 3.9 2500 0.7780 44.0946
0.0003 4.05 2600 0.7787 43.8906
0.0156 4.21 2700 0.7798 43.9091
0.0003 4.36 2800 0.7805 43.9114
0.0003 4.52 2900 0.7809 43.9230
0.0003 4.67 3000 0.7811 43.9230

Framework versions

  • Transformers 4.35.2
  • Pytorch 2.0.1+cu117
  • Datasets 2.15.0
  • Tokenizers 0.15.0