Downloads · 30 days
3
3% of all-time downloads
mms-1b-all-central-puebla-nahuatl
robertp408/mms-1b-all-central-puebla-nahuatl
mms-1b-all-central-puebla-nahuatl is a automatic speech recognition model from robertp408. Use it when you need speech turned into text. It is set up for transformers. The card lists the license as cc-by-nc-4.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
103
Public
Parameters
965M
30.9 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors3.9 GB · 100%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- License
- cc-by-nc-4.0
- Model type
- wav2vec2
- Access
- Public
- Created
- Nov 19, 2025
- Updated
- Nov 19, 2025
- SHA
- 4fb330e8
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. -->
mms-1b-all-central-puebla-nahuatl
This model is a fine-tuned version of facebook/mms-1b-all on the None dataset. It achieves the following results on the evaluation set:
- Loss: 3.7448
- Model Preparation Time: 0.0393
- Wer Ortho: 100.0
- Wer: 100.0
- Cer Ortho: 96.9899
- Cer: 99.0886
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: 0.001
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED 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: 50
- training_steps: 50
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Model Preparation Time | Wer Ortho | Wer | Cer Ortho | Cer |
|---|---|---|---|---|---|---|---|---|
| 14.6702 | 2.2727 | 50 | 3.7448 | 0.0393 | 100.0 | 100.0 | 96.9899 | 99.0886 |
Framework versions
- Transformers 4.57.1
- Pytorch 2.9.1+cu128
- Datasets 3.6.0
- Tokenizers 0.22.1
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- wav2vec2
- License
- cc-by-nc-4.0
- Created
- Nov 19, 2025
- Updated
- Nov 19, 2025