Downloads · 30 days
11
3% of all-time downloads
wav2vec2-large-xls-r-300m-ru
NLPVladimir/wav2vec2-large-xls-r-300m-ru
wav2vec2-large-xls-r-300m-ru is a automatic speech recognition model from NLPVladimir. 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
440
Public
Parameters
315M
13.9 GB on disk
Likes
2
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
- Jan 30, 2025
- Updated
- Jan 31, 2025
- SHA
- 01b0d51d
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-large-xls-r-300m-ru
This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the common_voice_17_0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.1965
- Wer: 0.1950
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: 18
- eval_batch_size: 24
- seed: 42
- gradient_accumulation_steps: 5
- total_train_batch_size: 90
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- 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 |
|---|---|---|---|---|
| 4.6582 | 1.2287 | 500 | 0.8055 | 0.7838 |
| 0.4342 | 2.4575 | 1000 | 0.3085 | 0.3492 |
| 0.2572 | 3.6862 | 1500 | 0.2439 | 0.2692 |
| 0.1731 | 4.9149 | 2000 | 0.2070 | 0.2266 |
| 0.1178 | 6.1426 | 2500 | 0.1965 | 0.1950 |
Framework versions
- Transformers 4.48.0
- Pytorch 2.5.1+cu124
- Datasets 3.2.0
- Tokenizers 0.21.0
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- wav2vec2
- License
- apache-2.0
- Created
- Jan 30, 2025
- Updated
- Jan 31, 2025