Downloads · 30 days
7
15% of all-time downloads
wav2vec2-large-xls-r-300m-tr-colab
markjosims/wav2vec2-large-xls-r-300m-tr-colab
wav2vec2-large-xls-r-300m-tr-colab is a automatic speech recognition model from markjosims. 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
46
Public
Repo size
10.1 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
- Jul 11, 2023
- Updated
- Jul 11, 2023
- SHA
- 2bdf2b1f
Datasets
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-large-xls-r-300m-tr-colab
This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the common_voice dataset. It achieves the following results on the evaluation set:
- Loss: 0.4346
- Wer: 0.3747
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: 16
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- 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: 500
- num_epochs: 30
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 3.9005 | 4.26 | 400 | 0.6917 | 0.7251 |
| 0.4032 | 8.51 | 800 | 0.4781 | 0.5286 |
| 0.1863 | 12.77 | 1200 | 0.4682 | 0.4690 |
| 0.1323 | 17.02 | 1600 | 0.4664 | 0.4483 |
| 0.1014 | 21.28 | 2000 | 0.4500 | 0.4124 |
| 0.0749 | 25.53 | 2400 | 0.4510 | 0.3909 |
| 0.0568 | 29.79 | 2800 | 0.4346 | 0.3747 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 1.18.3
- Tokenizers 0.13.3
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- wav2vec2
- License
- apache-2.0
- Created
- Jul 11, 2023
- Updated
- Jul 11, 2023