Downloads · 30 days
12
38% of all-time downloads
copt-300m-toratan-60
colorlessideas/copt-300m-toratan-60
copt-300m-toratan-60 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
32
Public
Parameters
315M
5 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
- Mar 10, 2025
- Updated
- Mar 10, 2025
- SHA
- 5d022d7c
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. -->
copt-300m-toratan-60
This model is a fine-tuned version of colorlessideas/xlsr-ulwa-continued-pretrain on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0600
- Cer: 0.0272
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 |
|---|---|---|---|---|
| 4.28 | 8.3333 | 400 | 1.4716 | 0.4029 |
| 1.1545 | 16.6667 | 800 | 0.3822 | 0.1181 |
| 0.489 | 25.0 | 1200 | 0.0600 | 0.0272 |
Framework versions
- Transformers 4.50.0.dev0
- Pytorch 2.5.1+cu124
- Datasets 3.3.2
- Tokenizers 0.21.0
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- wav2vec2
- License
- apache-2.0
- Created
- Mar 10, 2025
- Updated
- Mar 10, 2025