README.md

metadata

license: apache-2.0
base_model: Talha/URDU-ASR
tags:
  - generated_from_trainer
datasets:
  - common_voice_13_0
metrics:
  - wer
model-index:
  - name: wav2vec2-large-xlsr-53-ur-cv13
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: common_voice_13_0
          type: common_voice_13_0
          config: ur
          split: test
          args: ur
        metrics:
          - name: Wer
            type: wer
            value: 0.398777515571202

wav2vec2-large-xlsr-53-ur-cv13

This model is a fine-tuned version of Talha/URDU-ASR on the common_voice_13_0 dataset. It achieves the following results on the evaluation set:

• Loss: 0.4323
• Wer: 0.3988
• Cer: 0.1932

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: 3e-05
• train_batch_size: 16
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 32
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Wer	Cer
0.8043	1.46	250	0.5256	0.4023	0.1949
0.5435	2.92	500	0.4381	0.3965	0.1961
0.4827	4.39	750	0.4323	0.3988	0.1932

Framework versions

• Transformers 4.34.1
• Pytorch 2.1.0+cu118
• Datasets 2.14.6
• Tokenizers 0.14.1