Downloads · 30 days
6
15% of all-time downloads
wav2vec2-turkish-300m-5
tgrhn/wav2vec2-turkish-300m-5
wav2vec2-turkish-300m-5 is a automatic speech recognition model from tgrhn. 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
Parameters
316M
18.9 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors1.3 GB · 100%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- License
- apache-2.0
- Model type
- wav2vec2
- Access
- Public
- Created
- Apr 25, 2024
- Updated
- Apr 25, 2024
- SHA
- 0f9a2124
Base models
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-turkish-300m-5
This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the fleurs dataset. It achieves the following results on the evaluation set:
- Loss: 0.2648
- Wer: 0.2240
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: 4
- 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: 0.1
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 3.7591 | 0.6983 | 500 | 1.6294 | 0.9992 |
| 1.3537 | 1.3966 | 1000 | 0.4093 | 0.4643 |
| 0.5289 | 2.0950 | 1500 | 0.3083 | 0.3555 |
| 0.2647 | 2.7933 | 2000 | 0.2575 | 0.3179 |
| 0.1954 | 3.4916 | 2500 | 0.2527 | 0.2949 |
| 0.1719 | 4.1899 | 3000 | 0.2546 | 0.2785 |
| 0.1308 | 4.8883 | 3500 | 0.2385 | 0.2640 |
| 0.0943 | 5.5866 | 4000 | 0.2431 | 0.2626 |
| 0.0886 | 6.2849 | 4500 | 0.2503 | 0.2599 |
| 0.075 | 6.9832 | 5000 | 0.2470 | 0.2453 |
| 0.0734 | 7.6816 | 5500 | 0.2658 | 0.2402 |
| 0.0551 | 8.3799 | 6000 | 0.2613 | 0.2337 |
| 0.0534 | 9.0782 | 6500 | 0.2563 | 0.2242 |
| 0.05 | 9.7765 | 7000 | 0.2648 | 0.2240 |
Framework versions
- Transformers 4.40.0
- Pytorch 2.2.2+cu121
- Datasets 2.17.1
- Tokenizers 0.19.1
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- wav2vec2
- License
- apache-2.0
- Created
- Apr 25, 2024
- Updated
- Apr 25, 2024