metadata
license: apache-2.0
base_model: openai/whisper-large-v3
tags:
- generated_from_trainer
datasets:
- DewiBrynJones/commonvoice_18_0_cy
metrics:
- wer
model-index:
- name: whisper-large-v3-ft-cv-cy-train-all-plus-other-with-excluded
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: DewiBrynJones/commonvoice_18_0_cy default
type: DewiBrynJones/commonvoice_18_0_cy
args: default
metrics:
- name: Wer
type: wer
value: 0.1676010974591435
whisper-large-v3-ft-cv-cy-train-all-plus-other-with-excluded
This model is a fine-tuned version of openai/whisper-large-v3 on the DewiBrynJones/commonvoice_18_0_cy default dataset. It achieves the following results on the evaluation set:
- Loss: 0.3280
- Wer: 0.1676
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: 16
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- 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 |
|---|---|---|---|---|
| 0.1583 | 1.4144 | 1000 | 0.2562 | 0.2062 |
| 0.0675 | 2.8289 | 2000 | 0.2394 | 0.1849 |
| 0.0113 | 4.2433 | 3000 | 0.2729 | 0.1722 |
| 0.0036 | 5.6577 | 4000 | 0.3004 | 0.1705 |
| 0.0012 | 7.0721 | 5000 | 0.3280 | 0.1676 |
Framework versions
- Transformers 4.44.0
- Pytorch 2.4.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1