metadata
library_name: transformers
language:
- hi
license: apache-2.0
base_model: openai/whisper-small
tags:
- generated_from_trainer
datasets:
- procit008/STT_Datasetfacebookfemale
metrics:
- wer
model-index:
- name: Whisper Small Rajan
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: STT_Datasetfacebookfemale
type: procit008/STT_Datasetfacebookfemale
args: 'config: hi, split: test'
metrics:
- name: Wer
type: wer
value: 16.285201982913193
Whisper Small Rajan
This model is a fine-tuned version of openai/whisper-small on the STT_Datasetfacebookfemale dataset. It achieves the following results on the evaluation set:
- Loss: 0.5347
- Wer: 16.2852
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: 8
- seed: 42
- 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: 500
- training_steps: 4000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.156 | 2.1882 | 1000 | 0.4294 | 18.9431 |
| 0.0515 | 4.3764 | 2000 | 0.4644 | 16.8864 |
| 0.0099 | 6.5646 | 3000 | 0.5102 | 16.4540 |
| 0.0046 | 8.7527 | 4000 | 0.5347 | 16.2852 |
Framework versions
- Transformers 4.47.1
- Pytorch 2.4.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0