metadata
library_name: transformers
license: apache-2.0
base_model: KJnr/finetuned-whisper-small-V1.0.0
tags:
- generated_from_trainer
datasets:
- generator
metrics:
- wer
model-index:
- name: whisper-small-mult-2xt-continued
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: generator
type: generator
config: default
split: None
args: default
metrics:
- name: Wer
type: wer
value: 53.503161450843436
whisper-small-mult-2xt-continued
This model is a fine-tuned version of KJnr/finetuned-whisper-small-V1.0.0 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 0.4920
- Wer: 53.5032
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: 5e-06
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- distributed_type: multi-GPU
- num_devices: 2
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- total_eval_batch_size: 8
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.05
- training_steps: 3000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.268 | 0.3333 | 1000 | 0.5192 | 69.2031 |
| 0.2296 | 0.6667 | 2000 | 0.5010 | 49.9377 |
| 0.2441 | 1.0 | 3000 | 0.4920 | 53.5032 |
Framework versions
- Transformers 4.52.4
- Pytorch 2.5.1+cu124
- Datasets 3.6.0
- Tokenizers 0.21.0