metadata
language:
- hi
license: apache-2.0
tags:
- hf-asr-leaderboard
- generated_from_trainer
datasets:
- mozilla-foundation/common_voice_11_0
metrics:
- wer
model-index:
- name: Whisper Medium SW - Leinad Cybre
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: Common Voice 11.0
type: mozilla-foundation/common_voice_11_0
config: null
split: None
args: 'config: sw, split: test'
metrics:
- name: Wer
type: wer
value: 100.01149504563533
Whisper Medium SW - Leinad Cybre
This model is a fine-tuned version of openai/whisper-medium on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.3492
- Wer: 100.0115
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: 2
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- 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 |
|---|---|---|---|---|
| 0.3495 | 0.43 | 1000 | 0.4512 | 100.4414 |
| 0.2634 | 0.87 | 2000 | 0.3814 | 101.5449 |
| 0.1521 | 1.3 | 3000 | 0.3657 | 100.6736 |
| 0.1299 | 1.74 | 4000 | 0.3492 | 100.0115 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3