Downloads · 30 days
10
7% of all-time downloads
xls-r-300m-toratan-120
colorlessideas/xls-r-300m-toratan-120
xls-r-300m-toratan-120 is a automatic speech recognition model from colorlessideas. 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
145
Public
Parameters
315M
42.9 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
- Feb 6, 2025
- Updated
- Feb 13, 2025
- SHA
- 90759a4b
Base models
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. -->
xls-r-300m-toratan-120
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: 0.0100
- Cer: 0.0020
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: 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: 500
- num_epochs: 30
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Cer |
|---|---|---|---|---|
| 4.4395 | 4.1667 | 400 | 1.7448 | 0.4997 |
| 1.4406 | 8.3333 | 800 | 0.7917 | 0.2394 |
| 0.892 | 12.5 | 1200 | 0.4491 | 0.1448 |
| 0.5902 | 16.6667 | 1600 | 0.1968 | 0.0773 |
| 0.3741 | 20.8333 | 2000 | 0.0612 | 0.0240 |
| 0.2434 | 25.0 | 2400 | 0.0175 | 0.0065 |
| 0.1672 | 29.1667 | 2800 | 0.0100 | 0.0020 |
Framework versions
- Transformers 4.49.0.dev0
- 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
- Feb 6, 2025
- Updated
- Feb 13, 2025