metadata
base_model: openai/whisper-tiny.en
datasets:
- lalipa/jv_id_asr_split
library_name: transformers
license: apache-2.0
metrics:
- wer
tags:
- generated_from_trainer
model-index:
- name: finetune
results:
- task:
type: automatic-speech-recognition
name: Automatic Speech Recognition
dataset:
name: lalipa/jv_id_asr_split jv_id_asr_source
type: lalipa/jv_id_asr_split
config: jv_id_asr_source
split: validation
args: jv_id_asr_source
metrics:
- type: wer
value: 0.7835602493955974
name: Wer
finetune
This model is a fine-tuned version of openai/whisper-tiny.en on the lalipa/jv_id_asr_split jv_id_asr_source dataset. It achieves the following results on the evaluation set:
- Loss: 1.7784
- Wer: 0.7836
- Cer: 0.2535
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: 32
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 64
- optimizer: Use 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_steps: 30
- training_steps: 150
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
|---|---|---|---|---|---|
| 3.6903 | 0.2041 | 30 | 2.9875 | 1.0127 | 0.4365 |
| 2.533 | 0.4082 | 60 | 2.2360 | 0.8879 | 0.2921 |
| 2.0604 | 0.6122 | 90 | 1.9514 | 0.8253 | 0.2670 |
| 1.852 | 0.8163 | 120 | 1.8182 | 0.7949 | 0.2581 |
| 1.7929 | 1.0204 | 150 | 1.7784 | 0.7836 | 0.2535 |
Framework versions
- Transformers 4.46.0.dev0
- Pytorch 2.4.1
- Datasets 3.0.1
- Tokenizers 0.20.0