metadata
language:
- hi
license: apache-2.0
base_model: openai/whisper-small
tags:
- generated_from_trainer
datasets:
- mozilla-foundation/common_voice_11_0
metrics:
- wer
model-index:
- name: Whisper Small Hi - Ekogenie
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: Common Voice 11.0
type: mozilla-foundation/common_voice_11_0
config: yo
split: None
args: 'config: hi, split: test'
metrics:
- name: Wer
type: wer
value: 73.44256048771194
Whisper Small Hi - Ekogenie
This model is a fine-tuned version of openai/whisper-small on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.8922
- Wer: 73.4426
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: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 50
- training_steps: 1000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.6474 | 1.5385 | 200 | 0.8704 | 78.8341 |
| 0.3733 | 3.0769 | 400 | 0.7785 | 74.3284 |
| 0.1821 | 4.6154 | 600 | 0.8046 | 72.1661 |
| 0.0816 | 6.1538 | 800 | 0.8618 | 73.0996 |
| 0.0538 | 7.6923 | 1000 | 0.8922 | 73.4426 |
Framework versions
- Transformers 4.42.4
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1