Downloads · 30 days
42
1% of all-time downloads
whisper-medium-french
pierreguillou/whisper-medium-french
whisper-medium-french is a automatic speech recognition model from pierreguillou. Use it when you need speech turned into text. It is set up for transformers. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
4.5K
Public
Repo size
18.3 GB
Likes
9
Public
Repo makeup
Click a slice to open those files.
.bin3.1 GB · 100%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- License
- apache-2.0
- Model type
- whisper
- Access
- Public
- Created
- Dec 6, 2022
- Updated
- Dec 12, 2022
- SHA
- bd4dc9b2
Model card
From the Hugging Face model README
<!-- 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. -->
French Medium Whisper
This model is a fine-tuned version of openai/whisper-medium on the common_voice_11_0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.2664
- Wer (without normalization): 15.8969
- Wer (with normalization): 11.1406
Blog post
All information about this model in this blog post: Speech-to-Text & IA | Transcreva qualquer áudio para o português com o Whisper (OpenAI)... sem nenhum custo!.
New SOTA
The Normalized WER in the OpenAI Whisper article with the Common Voice 9.0 test dataset is 16.0.
As this test dataset is similar to the Common Voice 11.0 test dataset used to evaluate our model (WER and WER Norm), it means that our French Medium Whisper is better than the Medium Whisper model at transcribing audios French in text.
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 | Wer Norm |
|---|---|---|---|---|---|
| 0.2695 | 0.2 | 1000 | 0.3080 | 17.8083 | 12.9791 |
| 0.2099 | 0.4 | 2000 | 0.2981 | 17.4792 | 12.4242 |
| 0.1978 | 0.6 | 3000 | 0.2864 | 16.7767 | 12.0913 |
| 0.1455 | 0.8 | 4000 | 0.2752 | 16.4597 | 11.8966 |
| 0.1712 | 1.0 | 5000 | 0.2664 | 15.8969 | 11.1406 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu117
- Datasets 2.7.1.dev0
- Tokenizers 0.13.2
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- whisper
- License
- apache-2.0
- Languages
- fr
- Created
- Dec 6, 2022
- Updated
- Dec 12, 2022