language:
- es
license: apache-2.0
tags:
- whisper-event
- generated_from_trainer
datasets:
- mozilla-foundation/common_voice_11_0
- google/fleurs
- facebook/multilingual_librispeech
- facebook/voxpopuli
metrics:
- wer
base_model: openai/whisper-medium
model-index:
- name: openai/whisper-medium
results:
- task:
type: automatic-speech-recognition
name: Automatic Speech Recognition
dataset:
name: mozilla-foundation/common_voice_11_0 es
type: mozilla-foundation/common_voice_11_0
config: es
split: test
args: es
metrics:
- type: wer
value: 6.346473676004366
name: Wer
- type: cer
value: 2.1391
name: Cer
- task:
type: automatic-speech-recognition
name: Automatic Speech Recognition
dataset:
name: FLEURS ASR
type: google/fleurs
config: es_419
split: test
args: es
metrics:
- type: wer
value: 4.0266
name: WER
- type: cer
value: 1.6631
name: Cer
- task:
type: automatic-speech-recognition
name: Automatic Speech Recognition
dataset:
name: Multilingual LibriSpeech
type: facebook/multilingual_librispeech
config: spanish
split: test
args:
language: es
metrics:
- type: wer
value: 4.6644
name: WER
- type: cer
value: 1.7056
name: Cer
- task:
type: Automatic Speech Recognition
name: speech-recognition
dataset:
name: VoxPopuli
type: facebook/voxpopuli
config: es
split: test
args:
language: es
metrics:
- type: wer
value: 8.3668
name: WER
- type: cer
value: 5.479
name: Cer
openai/whisper-medium-mix-es
This model is a fine-tuned version of openai/whisper-medium on the mozilla-foundation/common_voice_11_0, google/fleurs, facebook/multilingual_librispeech and facebook/voxpopuli datasets. It achieves the following results on the evaluation set:
- Loss: 0.1344
- Wer: 6.3465
Using the evaluation script provided in the Whisper Sprint the model achieves these results on the test sets (WER):
google/fleurs: 4.0266 %
(python run_eval_whisper_streaming.py --model_id="deepdml/whisper-medium-mix-es" --dataset="google/fleurs" --config="es_419" --device=0 --language="es")facebook/multilingual_librispeech: 4.6644 %
(python run_eval_whisper_streaming.py --model_id="deepdml/whisper-medium-mix-es" --dataset="facebook/multilingual_librispeech" --config="spanish" --device=0 --language="es")facebook/voxpopuli: 8.3668 %
(python run_eval_whisper_streaming.py --model_id="deepdml/whisper-medium-mix-es" --dataset="facebook/voxpopuli" --config="es" --device=0 --language="es")
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
Training data used:
- mozilla-foundation/common_voice_11_0: es, train+validation
- google/fleurs: es_419, train
- facebook/multilingual_librispeech: spanish, train
- facebook/voxpopuli: es, train
Evaluating over test split from mozilla-foundation/common_voice_11_0 dataset.
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 32
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 5000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.266 | 0.2 | 1000 | 0.1657 | 8.0395 |
| 0.1394 | 0.4 | 2000 | 0.1539 | 7.3937 |
| 0.1316 | 0.6 | 3000 | 0.1452 | 6.9656 |
| 0.1165 | 0.8 | 4000 | 0.1392 | 6.5765 |
| 0.2816 | 1.0 | 5000 | 0.1344 | 6.3465 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu117
- Datasets 2.7.1.dev0
- Tokenizers 0.13.2