Downloads · 30 days
13
9% of all-time downloads
mms-multilingual-sa
kesbeast23/mms-multilingual-sa
mms-multilingual-sa is a automatic speech recognition model from kesbeast23. 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
137
Public
Parameters
965M
15.5 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 27, 2025
- Updated
- Dec 26, 2025
- SHA
- 6a3489f4
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-multilingual-sa
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: 0.3638
- Wer: 0.3932
- Cer: 0.1023
- Bertscore Precision: 0.9050
- Bertscore Recall: 0.9018
- Bertscore F1: 0.9033
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: 8
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 2
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- total_eval_batch_size: 16
- optimizer: Use 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: 500
- training_steps: 2000
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer | Bertscore Precision | Bertscore Recall | Bertscore F1 |
|---|---|---|---|---|---|---|---|---|
| 0.5792 | 1.9636 | 500 | 0.4358 | 0.4758 | 0.1232 | 0.8842 | 0.8811 | 0.8826 |
| 0.4905 | 3.9243 | 1000 | 0.3827 | 0.4174 | 0.1082 | 0.8992 | 0.8962 | 0.8976 |
| 0.4636 | 5.8850 | 1500 | 0.3707 | 0.3995 | 0.1044 | 0.9032 | 0.8991 | 0.9011 |
| 0.457 | 7.8456 | 2000 | 0.3638 | 0.3932 | 0.1023 | 0.9050 | 0.9018 | 0.9033 |
Framework versions
- Transformers 4.57.3
- Pytorch 2.9.1+cu128
- Datasets 4.4.2
- Tokenizers 0.22.1
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- wav2vec2
- License
- cc-by-nc-4.0
- Created
- Nov 27, 2025
- Updated
- Dec 26, 2025