README.md

metadata

license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - common_voice_13_0
metrics:
  - wer
model-index:
  - name: wav2vec2-large-xls-r-300m-hindi-colab-ysv
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: common_voice_13_0
          type: common_voice_13_0
          config: hi
          split: test
          args: hi
        metrics:
          - name: Wer
            type: wer
            value: 0.8740320510166052

wav2vec2-large-xls-r-300m-hindi-colab-ysv

This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the common_voice_13_0 dataset. It achieves the following results on the evaluation set:

• Loss: 1.6224
• Wer: 0.8740

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: 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: 4

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
5.7147	2.86	400	1.6224	0.8740

Framework versions

• Transformers 4.30.0
• Pytorch 2.1.2
• Datasets 2.18.0
• Tokenizers 0.13.3