sanchit-gandhi's picture
update model card README.md
096a2d5
---
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: 4.037333755183674
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# Whisper Small Es - Sanchit Gandhi
This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the Multilingual LibriSpeech dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1035
- Wer: 4.0373
## 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
- lr_scheduler_warmup_steps: 500
- training_steps: 4000
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| 0.1947 | 0.25 | 1000 | 0.1390 | 5.8261 |
| 0.1226 | 0.5 | 2000 | 0.1224 | 4.9978 |
| 0.1629 | 0.75 | 3000 | 0.1185 | 4.6543 |
| 0.1916 | 1.0 | 4000 | 0.1035 | 4.0373 |
### Framework versions
- Transformers 4.25.0.dev0
- Pytorch 1.12.0
- Datasets 2.6.2.dev0
- Tokenizers 0.12.1