metadata

language:
  - bsl
license: apache-2.0
base_model: openai/whisper-small
tags:
  - generated_from_trainer
datasets:
  - nesuri/sorsolingo-tts-bsl
model-index:
  - name: Sorsolingo-asr-bsl
    results: []

Sorsolingo-asr-bsl

This model is a fine-tuned version of openai/whisper-small on the sorsolingo-asr-bsl 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: 2e-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: 450
mixed_precision_training: Native AMP

Training results

Framework versions

Transformers 4.37.0.dev0
Pytorch 2.1.0+cu121
Datasets 2.15.0
Tokenizers 0.15.0