README.md

metadata

base_model: wav2vec2-pretrained-base-gumbelVQ
tags:
  - automatic-speech-recognition
  - timit_asr
  - generated_from_trainer
datasets:
  - timit_asr
metrics:
  - wer
model-index:
  - name: wav2vec2-base-gumbelVQ-timit-fine-tuned
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: TIMIT_ASR - NA
          type: timit_asr
          config: clean
          split: test
          args: 'Config: na, Training split: train, Eval split: test'
        metrics:
          - name: Wer
            type: wer
            value: 0.4901798635517883

wav2vec2-base-gumbelVQ-timit-fine-tuned

This model is a fine-tuned version of wav2vec2-pretrained-base-gumbelVQ on the TIMIT_ASR - NA dataset. It achieves the following results on the evaluation set:

• Loss: 0.7549
• Wer: 0.4902

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: 0.0001
• train_batch_size: 32
• eval_batch_size: 1
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 1000
• num_epochs: 20.0

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.4628	10.0	1450	0.6779	0.5171
0.3036	20.0	2900	0.7549	0.4902

Framework versions

• Transformers 4.36.2
• Pytorch 2.3.0.dev20231229+cu118
• Datasets 2.16.0
• Tokenizers 0.15.0