Downloads · 30 days
15
7% of all-time downloads
wav2vec2-common_voice-it_en-demo
AlbertoFor/wav2vec2-common_voice-it_en-demo
wav2vec2-common_voice-it_en-demo is a automatic speech recognition model from AlbertoFor. 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
201
Public
Repo size
24 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin1.3 GB · 100%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- License
- apache-2.0
- Model type
- wav2vec2
- Access
- Public
- Created
- May 23, 2023
- Updated
- May 23, 2023
- SHA
- 6e01fd23
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-common_voice-it_en-demo
This model is a fine-tuned version of facebook/wav2vec2-large-xlsr-53 on the COMMON_VOICE - IT dataset. It achieves the following results on the evaluation set:
- Loss: 0.1128
- Wer: 0.0947
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: 0.0003
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 10.0
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| No log | 0.53 | 400 | 1.2299 | 0.7601 |
| 3.6201 | 1.07 | 800 | 0.4973 | 0.4249 |
| 0.6369 | 1.6 | 1200 | 0.3748 | 0.3481 |
| 0.455 | 2.13 | 1600 | 0.2834 | 0.2644 |
| 0.3177 | 2.67 | 2000 | 0.2426 | 0.2234 |
| 0.3177 | 3.2 | 2400 | 0.1868 | 0.1862 |
| 0.2697 | 3.73 | 2800 | 0.1915 | 0.1847 |
| 0.2363 | 4.27 | 3200 | 0.1667 | 0.1608 |
| 0.1795 | 4.8 | 3600 | 0.1458 | 0.1429 |
| 0.1636 | 5.33 | 4000 | 0.1468 | 0.1388 |
| 0.1636 | 5.87 | 4400 | 0.1351 | 0.1314 |
| 0.1445 | 6.4 | 4800 | 0.1163 | 0.1108 |
| 0.1153 | 6.93 | 5200 | 0.1093 | 0.1088 |
| 0.1011 | 7.47 | 5600 | 0.1233 | 0.1141 |
| 0.0978 | 8.0 | 6000 | 0.1147 | 0.1041 |
| 0.0978 | 8.53 | 6400 | 0.1112 | 0.0984 |
| 0.0748 | 9.07 | 6800 | 0.1100 | 0.0938 |
| 0.075 | 9.6 | 7200 | 0.1180 | 0.0960 |
Framework versions
- Transformers 4.29.2
- Pytorch 2.0.1+cu117
- Datasets 2.12.0
- Tokenizers 0.11.0
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- wav2vec2
- License
- apache-2.0
- Languages
- it
- Created
- May 23, 2023
- Updated
- May 23, 2023