metadata
language:
- es
license: apache-2.0
tags:
- hf-asr-leaderboard
- generated_from_trainer
datasets:
- facebook/multilingual_librispeech
metrics:
- wer
model-index:
- name: Whisper Small Es - Sanchit Gandhi
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: Multilingual LibriSpeech
type: facebook/multilingual_librispeech
args: 'config: es, split: test'
metrics:
- name: Wer
type: wer
value: 4.124340388026983
Whisper Small Es - Sanchit Gandhi
This model is a fine-tuned version of openai/whisper-medium on the Multilingual LibriSpeech dataset. It achieves the following results on the evaluation set:
- Loss: 0.1024
- Wer: 4.1243
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: 4
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 5000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.1887 | 0.2 | 1000 | 0.1329 | 5.4249 |
| 0.123 | 0.4 | 2000 | 0.1212 | 4.9639 |
| 0.1594 | 0.6 | 3000 | 0.1144 | 4.3210 |
| 0.1777 | 0.8 | 4000 | 0.1116 | 4.5379 |
| 0.2469 | 1.0 | 5000 | 0.1024 | 4.1243 |
Framework versions
- Transformers 4.25.0.dev0
- Pytorch 1.12.0
- Datasets 2.6.2.dev0
- Tokenizers 0.12.1