Hugging Face's logo

oyqiz
/
uzbek_stt_1_version

Automatic Speech Recognition
Transformers
PyTorch
Uzbek
wav2vec2
mozilla-foundation/common_voice_10_0
Generated from Trainer
AIRI_UZ
Inference Endpoints
Model card Files Community
uzbek_stt_1_version / README.md
oyqiz's picture
oyqiz
update model card README.md
b4dfbf0
preview code
|
raw
history blame
1.81 kB
metadata
language:
  - uz
license: apache-2.0
tags:
  - automatic-speech-recognition
  - mozilla-foundation/common_voice_10_0
  - generated_from_trainer
datasets:
  - common_voice_10_0
model-index:
  - name: uzbek_stt
    results: []

uzbek_stt

This model is a fine-tuned version of facebook/wav2vec2-base on the MOZILLA-FOUNDATION/COMMON_VOICE_10_0 - UZ dataset. It achieves the following results on the evaluation set:

  • Loss: 0.5763
  • Wer: 0.4502

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: 0.0003
  • train_batch_size: 4
  • eval_batch_size: 8
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 2
  • total_train_batch_size: 8
  • total_eval_batch_size: 16
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 500
  • num_epochs: 15.0
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer
0.4736 3.4 10000 0.6247 0.6362
0.3392 6.8 20000 0.7254 0.5605
0.2085 10.19 30000 0.5465 0.5097
0.1387 13.59 40000 0.5984 0.4632

Framework versions

  • Transformers 4.22.0.dev0
  • Pytorch 1.10.0+cu113
  • Datasets 2.4.0
  • Tokenizers 0.12.1