metadata

license: apache-2.0
tags:
  - generated_from_trainer
base_model: openai/whisper-small
datasets:
  - verba_lex_voice
metrics:
  - wer
model-index:
  - name: verbalex-hi
    results:
      - task:
          type: automatic-speech-recognition
          name: Automatic Speech Recognition
        dataset:
          name: verba_lex_voice
          type: verba_lex_voice
          config: hi
          split: test
          args: hi
        metrics:
          - type: wer
            value: 1.6019256308100929
            name: Wer

verbalex-hi

This model is a fine-tuned version of openai/whisper-small on the verba_lex_voice dataset. It achieves the following results on the evaluation set:

Loss: 0.0554
Wer: 1.6019

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: 16
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: 500
training_steps: 5000
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0011	5.0505	1000	0.0504	1.7762
0.0001	10.1010	2000	0.0529	1.6268
0.0001	15.1515	3000	0.0541	1.6434
0.0001	20.2020	4000	0.0550	1.6102
0.0	25.2525	5000	0.0554	1.6019

Framework versions

Transformers 4.40.2
Pytorch 2.1.2
Datasets 2.16.0
Tokenizers 0.19.1