metadata

license: cc-by-nc-4.0
tags:
  - generated_from_trainer
datasets:
  - spgispeech
base_model: facebook/mms-1b-all
model-index:
  - name: wav2vec2-large-mms-1b-no_LSAH-SPGI-S
    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: 16.64
            name: WER
          - type: cer
            value: 4.64
            name: CER

wav2vec2-large-mms-1b-no_LSAH-SPGI-S

This model is a fine-tuned version of facebook/mms-1b-all on the spgispeech 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: 32
eval_batch_size: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 100
training_steps: 2409
mixed_precision_training: Native AMP

Training results

Framework versions

Transformers 4.36.0.dev0
Pytorch 1.12.1+cu116
Datasets 2.4.0
Tokenizers 0.15.0