README.md

metadata

license: apache-2.0
base_model: facebook/wav2vec2-base
tags:
  - generated_from_trainer
datasets:
  - ami
metrics:
  - wer
model-index:
  - name: my_awesome_asr_mind_model
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: ami
          type: ami
          config: ihm
          split: None
          args: ihm
        metrics:
          - name: Wer
            type: wer
            value: 1.0212765957446808

my_awesome_asr_mind_model

This model is a fine-tuned version of facebook/wav2vec2-base on the ami dataset. It achieves the following results on the evaluation set:

• Loss: 2.8963
• Wer: 1.0213

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: 1e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 16
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• training_steps: 4000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
2.8483	200.0	1000	2.9585	1.0
2.3611	400.0	2000	2.8366	1.0
1.9727	600.0	3000	2.8479	1.0160
1.8014	800.0	4000	2.8963	1.0213

Framework versions

• Transformers 4.42.3
• Pytorch 2.3.1
• Datasets 2.20.0
• Tokenizers 0.19.1