deepdml's picture
Update README.md
3031cda
|
raw
history blame
4.27 kB
---
language:
- fr
tags:
- whisper-event
- generated_from_trainer
datasets:
- mozilla-foundation/common_voice_11_0
metrics:
- wer
model-index:
- name: deepdml/whisper-medium-mix-fr
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: mozilla-foundation/common_voice_11_0 fr
type: mozilla-foundation/common_voice_11_0
config: fr
split: test
args: fr
metrics:
- name: Wer
type: wer
value: 11.227820307400155
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: FLEURS ASR
type: google/fleurs
config: fr_fr
split: test
args: fr
metrics:
- name: WER
type: wer
value: 9.3526
- name: Cer
type: cer
value: 4.144
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: Multilingual LibriSpeech
type: facebook/multilingual_librispeech
config: french
split: test
args:
language: fr
metrics:
- name: WER
type: wer
value: 6.3468
- name: Cer
type: cer
value: 3.1561
- task:
type: Automatic Speech Recognition
name: speech-recognition
dataset:
name: VoxPopuli
type: facebook/voxpopuli
config: fr
split: test
args:
language: fr
metrics:
- name: WER
type: wer
value: 10.0653
- name: Cer
type: cer
value: 6.5456
---
<!-- 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. -->
# deepdml/whisper-medium-mix-fr
This model is a fine-tuned version of [deepdml/whisper-medium-mix-fr](https://huggingface.co/deepdml/whisper-medium-mix-fr) 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: 0.2599
- Wer: 11.2278
Using the [evalutaion script](https://github.com/huggingface/community-events/blob/main/whisper-fine-tuning-event/run_eval_whisper_streaming.py) provided in the Whisper Sprint the model achieves these results on the test sets (WER):
- **google/fleurs: 9.3526 %**
(python run_eval_whisper_streaming.py --model_id="deepdml/whisper-medium-mix-fr" --dataset="google/fleurs" --config="fr_fr" --device=0 --language="fr")
- **facebook/multilingual_librispeech: 6.3468 %**
(python run_eval_whisper_streaming.py --model_id="deepdml/whisper-medium-mix-fr" --dataset="facebook/multilingual_librispeech" --config="french" --device=0 --language="fr")
- **facebook/voxpopuli: 10.0653 %**
(python run_eval_whisper_streaming.py --model_id="deepdml/whisper-medium-mix-fr" --dataset="facebook/voxpopuli" --config="fr" --device=0 --language="fr")
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
Training data used:
- **mozilla-foundation/common_voice_11_0:** fr, train+validation
- **google/fleurs:** fr_fr, train
- **facebook/multilingual_librispeech:** french, train
- **facebook/voxpopuli:** fr, 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: 4000
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|:-------------:|:-----:|:----:|:---------------:|:-------:|
| 0.0855 | 0.25 | 1000 | 0.2826 | 12.4230 |
| 0.0569 | 0.5 | 2000 | 0.2768 | 11.9577 |
| 0.0724 | 0.75 | 3000 | 0.2670 | 11.6106 |
| 0.069 | 1.0 | 4000 | 0.2599 | 11.2278 |
### Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu117
- Datasets 2.7.1.dev0
- Tokenizers 0.13.2