README.md

metadata

base_model: vinai/PhoWhisper-medium
tags:
  - generated_from_trainer
model-index:
  - name: PhoWhisper-medium-vispeech-classifier-v4
    results: []
datasets:
  - hr16/ViSpeech-Gender-Dialect-Classification
language:
  - vi
metrics:
  - accuracy
library_name: transformers
pipeline_tag: audio-classification

PhoWhisper-medium-vispeech-classifier-v4

This model is a fine-tuned version of vinai/PhoWhisper-medium on the hr16/ViSpeech-Gender-Dialect-Classification dataset. It achieves the following results on the evaluation set:

• eval_loss: 0.3675
• eval_accuracy: 0.9131
• eval_runtime: 574.4362
• eval_samples_per_second: 5.191
• eval_steps_per_second: 0.649
• epoch: 3.0
• step: 4407

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: 3e-06
• train_batch_size: 8
• 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_ratio: 0.1
• num_epochs: 5
• mixed_precision_training: Native AMP

Framework versions

• Transformers 4.41.2
• Pytorch 2.1.2
• Datasets 2.19.2
• Tokenizers 0.19.1