metadata

base_model: openai/whisper-large-v3
datasets:
  - common_voice_16_1
library_name: peft
license: apache-2.0
tags:
  - generated_from_trainer
model-index:
  - name: whisper-large-v3-finetuned-finetuned
    results: []

whisper-large-v3-finetuned-finetuned

This model is a fine-tuned version of openai/whisper-large-v3 on the common_voice_16_1 dataset. It achieves the following results on the evaluation set:

eval_loss: 2.0060
eval_wer: 65.7407
eval_runtime: 179.8302
eval_samples_per_second: 0.139
eval_steps_per_second: 0.022
epoch: 28.02
step: 200

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: 8
eval_batch_size: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: constant_with_warmup
lr_scheduler_warmup_steps: 20
training_steps: 200
mixed_precision_training: Native AMP

Framework versions

PEFT 0.11.1
Transformers 4.42.3
Pytorch 2.4.0
Datasets 2.19.2
Tokenizers 0.19.1