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: 4.426038712301834

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: 0.1107
Wer: 4.4260

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: 2500
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.186	0.2	500	0.1487	6.1786
0.1947	0.4	1000	0.1350	5.5910
0.3566	0.6	1500	0.1242	4.9537
0.1237	0.8	2000	0.1181	4.8001
0.1902	1.0	2500	0.1107	4.4260

Framework versions

Transformers 4.25.0.dev0
Pytorch 1.12.0
Datasets 2.6.2.dev0
Tokenizers 0.12.1