Downloads · 30 days
8
20% of all-time downloads
dys_asr_xlsr
pnparam/dys_asr_xlsr
dys_asr_xlsr is a automatic speech recognition model from pnparam. 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
41
Public
Repo size
2.5 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
- Feb 17, 2023
- Updated
- Feb 19, 2023
- SHA
- 1a1b95dd
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. -->
dys_asr_xlsr
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: 0.0468
- Wer: 1.3583
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: 0.0001
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 1000
- num_epochs: 7
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 9.4773 | 1.36 | 500 | 3.1298 | 1.0 |
| 2.6931 | 2.72 | 1000 | 1.7611 | 2.7726 |
| 1.0777 | 4.09 | 1500 | 0.3407 | 2.2212 |
| 0.227 | 5.45 | 2000 | 0.0824 | 1.6604 |
| 0.098 | 6.81 | 2500 | 0.0468 | 1.3583 |
Framework versions
- Transformers 4.17.0
- Pytorch 1.13.1+cu116
- Datasets 1.18.3
- Tokenizers 0.13.2
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- wav2vec2
- License
- apache-2.0
- Created
- Feb 17, 2023
- Updated
- Feb 19, 2023