README.md

metadata

base_model: ylacombe/w2v-bert-2.0
tags:
  - generated_from_trainer
metrics:
  - wer
model-index:
  - name: w2v-bert-2.0-ukrainian-colab-CV16.0
    results:
      - task:
          name: Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: Common Voice uk
          type: common_voice
          args: uk
        metrics:
          - name: Test WER
            type: wer
            value: 9.81
license: mit
datasets:
  - common_voice
language:
  - uk
pipeline_tag: automatic-speech-recognition

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

This model is a fine-tuned version of ylacombe/w2v-bert-2.0 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.1386
• Wer: 0.0981

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: 64
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 128
• 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
0.8074	1.98	520	0.1498	0.1461
0.0694	3.96	1040	0.1243	0.1213
0.0369	5.94	1560	0.1221	0.1059
0.0214	7.92	2080	0.1257	0.0987
0.0115	9.9	2600	0.1386	0.0981

Framework versions

• Transformers 4.37.0.dev0
• Pytorch 1.12.1+cu116
• Datasets 2.4.0
• Tokenizers 0.15.1