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
a6d87bb
preview code
|
raw
history blame
No virus
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: 0.7773
  • Wer: 58.2147

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: 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
0.0106 0.16 100 0.7024 44.3125
0.0107 0.31 200 0.7246 46.4665
0.0121 0.47 300 0.7213 44.8249
0.0096 0.62 400 0.7252 48.7294
0.0118 0.78 500 0.7118 47.6837
0.011 0.93 600 0.7221 47.6119
0.0058 1.09 700 0.7494 46.9117
0.0051 1.25 800 0.7611 46.6844
0.009 1.4 900 0.7271 47.2919
0.0077 1.56 1000 0.7287 58.6274
0.0058 1.71 1100 0.7582 64.5653
0.0067 1.87 1200 0.7135 66.7841
0.0031 2.03 1300 0.7395 61.1755
0.0033 2.18 1400 0.7353 62.7568
0.0025 2.34 1500 0.7535 68.1080
0.0022 2.49 1600 0.7521 63.5126
0.0151 2.65 1700 0.7546 71.5140
0.0022 2.8 1800 0.7470 79.6058
0.0017 2.96 1900 0.7286 70.0348
0.0008 3.12 2000 0.7544 66.4433
0.0007 3.27 2100 0.7618 60.4336
0.0004 3.43 2200 0.7672 64.8505
0.0015 3.58 2300 0.7853 60.2017
0.0008 3.74 2400 0.7719 59.2233
0.0003 3.9 2500 0.7537 60.1414
0.0002 4.05 2600 0.7656 59.9490
0.0087 4.21 2700 0.7726 59.2140
0.0003 4.36 2800 0.7750 59.6661
0.0002 4.52 2900 0.7766 58.8036
0.0002 4.67 3000 0.7773 58.2147

Framework versions

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