metadata
library_name: transformers
license: apache-2.0
base_model: openai/whisper-tiny
tags:
- generated_from_trainer
datasets:
- audiofolder
metrics:
- wer
model-index:
- name: whisper-tiny-as-LDCIL-sentenceAligned_ChotaTesting
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: audiofolder
type: audiofolder
config: default
split: train
args: default
metrics:
- name: Wer
type: wer
value: 125.97765363128492
whisper-tiny-as-LDCIL-sentenceAligned_ChotaTesting
This model is a fine-tuned version of openai/whisper-tiny on the audiofolder dataset. It achieves the following results on the evaluation set:
- Loss: 1.3640
- Wer: 125.9777
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
- 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: constant_with_warmup
- lr_scheduler_warmup_steps: 20
- training_steps: 100
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| No log | 0.4 | 20 | 1.8993 | 156.5992 |
| 2.2744 | 0.8 | 40 | 1.5240 | 183.4846 |
| 1.5738 | 1.2 | 60 | 1.4388 | 129.3296 |
| 1.432 | 1.6 | 80 | 1.3968 | 137.8142 |
| 1.364 | 2.0 | 100 | 1.3640 | 125.9777 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.4.0+cu121
- Datasets 3.1.0
- Tokenizers 0.20.3