metadata
library_name: transformers
language:
- hi
license: apache-2.0
base_model: openai/whisper-medium
tags:
- generated_from_trainer
datasets:
- mozilla-foundation/common_voice_11_0
metrics:
- wer
model-index:
- name: 'Whisper Medium Hi - Illuminati014 '
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: Common_voice_modified
type: mozilla-foundation/common_voice_11_0
config: hi
split: None
args: 'config: hi, split: test'
metrics:
- name: Wer
type: wer
value: 31.030015115525806
Whisper Medium Hi - Illuminati014
This model is a fine-tuned version of openai/whisper-medium on the Common_voice_modified dataset. It achieves the following results on the evaluation set:
- Loss: 0.5733
- Wer: 31.0300
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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- 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_steps: 500
- training_steps: 4000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.0087 | 12.1951 | 1000 | 0.4534 | 32.1961 |
| 0.0004 | 24.3902 | 2000 | 0.5305 | 31.3755 |
| 0.0001 | 36.5854 | 3000 | 0.5546 | 30.9652 |
| 0.0001 | 48.7805 | 4000 | 0.5733 | 31.0300 |
Framework versions
- Transformers 4.49.0
- Pytorch 2.5.1+cu124
- Datasets 3.3.2
- Tokenizers 0.21.0