Downloads · 30 days
1.6K
1% of all-time downloads
wav2vec2-xls-r-300m-phoneme
vitouphy/wav2vec2-xls-r-300m-phoneme
wav2vec2-xls-r-300m-phoneme is a automatic speech recognition model from vitouphy. 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
266K
Public
Parameters
315M
10.1 GB on disk
Likes
6
Public
Repo makeup
Click a slice to open those files.
.bin1.3 GB · 50%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- License
- apache-2.0
- Model type
- wav2vec2
- Access
- Public
- Created
- May 19, 2022
- Updated
- May 13, 2023
- SHA
- bf9913bf
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. -->
wav2vec2-xls-r-300m-phoneme
This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3327
- Cer: 0.1332
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: 3e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- 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: 2000
- training_steps: 7000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Cer |
|---|---|---|---|---|
| 3.4324 | 1.32 | 1000 | 3.3693 | 0.9091 |
| 2.1751 | 2.65 | 2000 | 1.1382 | 0.2397 |
| 1.3986 | 3.97 | 3000 | 0.4886 | 0.1452 |
| 1.2285 | 5.3 | 4000 | 0.3842 | 0.1351 |
| 1.142 | 6.62 | 5000 | 0.3505 | 0.1349 |
| 1.1075 | 7.95 | 6000 | 0.3323 | 0.1317 |
| 1.0867 | 9.27 | 7000 | 0.3265 | 0.1315 |
Framework versions
- Transformers 4.17.0.dev0
- Pytorch 1.10.2+cu102
- Datasets 1.18.2.dev0
- Tokenizers 0.11.0
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- wav2vec2
- License
- apache-2.0
- Created
- May 19, 2022
- Updated
- May 13, 2023