ndeclarke's picture
Upload tokenizer
e1b63ab verified
|
raw
history blame
2.49 kB
metadata
base_model: facebook/mms-1b-all
datasets:
  - common_voice_17_0
library_name: transformers
license: cc-by-nc-4.0
metrics:
  - wer
  - bleu
tags:
  - generated_from_trainer
model-index:
  - name: wav2vec2-mms-1b-CV17.0-training_set_variations
    results:
      - task:
          type: automatic-speech-recognition
          name: Automatic Speech Recognition
        dataset:
          name: common_voice_17_0
          type: common_voice_17_0
          config: ta
          split: >-
            validation[:5%]+validation[20%:25%]+validation[60%:65%]+validation[90%:]
          args: ta
        metrics:
          - type: wer
            value: 1.0594668189204621
            name: Wer
          - type: bleu
            value: 0
            name: Bleu

wav2vec2-mms-1b-CV17.0-training_set_variations

This model is a fine-tuned version of facebook/mms-1b-all on the common_voice_17_0 dataset. It achieves the following results on the evaluation set:

  • Loss: 8.6744
  • Wer: 1.0595
  • Cer: 0.7507
  • Bleu: 0.0

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: 0.001
  • 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_ratio: 0.15
  • training_steps: 2000
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer Cer Bleu
8.9593 25.0 100 4.6860 1.0 0.9446 0.0
3.3283 50.0 200 5.0896 1.0199 0.8069 0.0
2.6345 75.0 300 6.0989 1.0176 0.7693 0.0
1.963 100.0 400 6.7363 1.0451 0.7518 0.0
1.3091 125.0 500 7.8085 1.0284 0.7587 0.0
0.912 150.0 600 8.6744 1.0595 0.7507 0.0

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.4.1+cu121
  • Datasets 3.0.0
  • Tokenizers 0.19.1