Downloads · 30 days
3
1% of all-time downloads
wav2vec2-large-xls-r-300m-yo-colab-charb
charbossly/wav2vec2-large-xls-r-300m-yo-colab-charb
wav2vec2-large-xls-r-300m-yo-colab-charb is a automatic speech recognition model from charbossly. 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
299
Public
Parameters
315M
6.3 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
- Jun 6, 2024
- Updated
- Jun 11, 2024
- SHA
- 553c5212
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-yo-colab-charb
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: 1.5786
- Wer: 0.9970
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
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.4425 | 6.1538 | 400 | 1.1643 | 1.0 |
| 0.3455 | 12.3077 | 800 | 1.3662 | 1.0 |
| 0.1576 | 18.4615 | 1200 | 1.3859 | 0.9990 |
| 0.0764 | 24.6154 | 1600 | 1.5786 | 0.9970 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.2
- Tokenizers 0.19.1
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- wav2vec2
- License
- apache-2.0
- Created
- Jun 6, 2024
- Updated
- Jun 11, 2024