Jungwonchang's picture
Update metadata with huggingface_hub
e19a048
metadata
license: cc-by-nc-4.0
tags:
  - generated_from_trainer
datasets:
  - spgispeech_xs
base_model: facebook/mms-300m
model-index:
  - name: wav2vec2-large-mms-300m-FULL-SPGI-xs
    results:
      - task:
          type: automatic-speech-recognition
          name: Automatic Speech Recognition
        dataset:
          name: Test set for spgispeech
          type: kensho/spgispeech
          config: test
          split: test
        metrics:
          - type: wer
            value: 100
            name: WER
          - type: cer
            value: 99.3
            name: CER

wav2vec2-large-mms-300m-FULL-SPGI-xs

This model is a fine-tuned version of facebook/mms-300m on the spgispeech_xs dataset.

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: 8
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 4
  • 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: 100
  • training_steps: 120
  • mixed_precision_training: Native AMP

Training results

Framework versions

  • Transformers 4.36.0.dev0
  • Pytorch 2.1.0+cu118
  • Datasets 2.15.0
  • Tokenizers 0.15.0