README.md

metadata

license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - common_voice
metrics:
  - wer
model-index:
  - name: wav2vec2-large-xls-r-300m-TAMIL-colab
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: common_voice
          type: common_voice
          config: ta
          split: train+validation
          args: ta
        metrics:
          - name: Wer
            type: wer
            value: 0.9398623015315442

wav2vec2-large-xls-r-300m-TAMIL-colab

This model is a fine-tuned version of facebook/wav2vec2-large-xlsr-53 on the common_voice dataset. It achieves the following results on the evaluation set:

• Loss: 1.3785
• Wer: 0.9399

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
• gradient_accumulation_steps: 2
• total_train_batch_size: 8
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• num_epochs: 30

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
6.0959	9.99	400	2.2197	1.0
0.8365	19.99	800	1.3999	0.9362
0.2329	29.99	1200	1.3785	0.9399

Framework versions

• Transformers 4.25.0
• Pytorch 1.10.0+cu113
• Datasets 1.18.3
• Tokenizers 0.13.3