README.md

metadata

base_model: ylacombe/w2v-bert-2.0
tags:
  - generated_from_trainer
datasets:
  - common_voice_16_0
metrics:
  - wer
model-index:
  - name: w2v-bert-2.0-mongolian-colab-CV16.0
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: common_voice_16_0
          type: common_voice_16_0
          config: mn
          split: test
          args: mn
        metrics:
          - name: Wer
            type: wer
            value: 0.3382089065303681

w2v-bert-2.0-mongolian-colab-CV16.0

This model is a fine-tuned version of ylacombe/w2v-bert-2.0 on the common_voice_16_0 dataset. It achieves the following results on the evaluation set:

• Loss: 0.5279
• Wer: 0.3382

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: 5e-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: 10
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
2.0592	2.37	300	0.7052	0.5907
0.3893	4.74	600	0.5848	0.4508
0.1926	7.11	900	0.5277	0.3830
0.0857	9.49	1200	0.5279	0.3382

Framework versions

• Transformers 4.37.0.dev0
• Pytorch 2.1.0+cu121
• Datasets 2.16.1
• Tokenizers 0.15.1