metadata
language:
- en
license: apache-2.0
base_model: openai/whisper-large-v3
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: ./whisper-large-cit-synth-do0.15-wd0-lr1e-05
results: []
./whisper-large-cit-synth-do0.15-wd0-lr1e-05
This model is a fine-tuned version of openai/whisper-large-v3 on the SF 200 synth 2000 dataset. It achieves the following results on the evaluation set:
- Loss: 0.3455
- Wer: 15.0359
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: 4
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- gradient_accumulation_steps: 4
- 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: 100
- training_steps: 300
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Wer |
---|---|---|---|---|
0.5226 | 0.4040 | 50 | 0.3027 | 17.5235 |
0.2202 | 0.8081 | 100 | 0.2734 | 16.6022 |
0.1105 | 1.2121 | 150 | 0.2876 | 16.1047 |
0.0613 | 1.6162 | 200 | 0.2642 | 14.3542 |
0.0504 | 2.0202 | 250 | 0.3025 | 14.3910 |
0.0158 | 2.4242 | 300 | 0.3455 | 15.0359 |
Framework versions
- Transformers 4.41.2
- Pytorch 1.13.1+cu117
- Datasets 2.19.2
- Tokenizers 0.19.1