README.md

metadata

license: apache-2.0
base_model: facebook/wav2vec2-large-xlsr-53
tags:
  - generated_from_trainer
datasets:
  - common_voice_13_0
metrics:
  - wer
model-index:
  - name: Marathi_ASR_using_xlsr_wav2vec
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: common_voice_13_0
          type: common_voice_13_0
          config: mr
          split: test
          args: mr
        metrics:
          - name: Wer
            type: wer
            value: 0.787176724137931

Marathi_ASR_using_xlsr_wav2vec

This model is a fine-tuned version of facebook/wav2vec2-large-xlsr-53 on the common_voice_13_0 dataset. It achieves the following results on the evaluation set:

• Loss: 0.7676
• Wer: 0.7872

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: 30
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
6.5921	10.6667	400	3.3151	1.0021
2.0358	21.3333	800	0.7676	0.7872

Framework versions

• Transformers 4.40.0
• Pytorch 2.1.2
• Datasets 2.19.0
• Tokenizers 0.19.1