Downloads · 30 days
8
20% of all-time downloads
ssc-el-CY-mms-model-mix-adapt-max
ctaguchi/ssc-el-CY-mms-model-mix-adapt-max
ssc-el-CY-mms-model-mix-adapt-max is a automatic speech recognition model from ctaguchi. 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
40
Public
Parameters
965M
61.8 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
- Dec 5, 2025
- Updated
- Dec 5, 2025
- SHA
- 06dd885f
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. -->
ssc-el-CY-mms-model-mix-adapt-max
This model is a fine-tuned version of facebook/mms-1b-all on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.3308
- Cer: 0.2323
- Wer: 0.6059
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: 2
- total_train_batch_size: 16
- 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: 100
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Cer | Wer |
|---|---|---|---|---|---|
| 1.3274 | 0.3265 | 200 | 1.3596 | 0.3034 | 0.7994 |
| 1.1117 | 0.6531 | 400 | 1.3266 | 0.2698 | 0.7272 |
| 1.0661 | 0.9796 | 600 | 1.2708 | 0.2526 | 0.6822 |
| 1.0701 | 1.3053 | 800 | 1.3483 | 0.2587 | 0.6955 |
| 0.9163 | 1.6318 | 1000 | 1.3488 | 0.2502 | 0.6549 |
| 0.9005 | 1.9584 | 1200 | 1.3639 | 0.2487 | 0.6600 |
| 0.8301 | 2.2841 | 1400 | 1.3388 | 0.2447 | 0.6339 |
| 0.8878 | 2.6106 | 1600 | 1.3057 | 0.2348 | 0.6285 |
| 0.8899 | 2.9371 | 1800 | 1.3062 | 0.2408 | 0.6295 |
| 0.8035 | 3.2629 | 2000 | 1.3022 | 0.2413 | 0.6372 |
| 0.8172 | 3.5894 | 2200 | 1.3599 | 0.2319 | 0.6133 |
| 0.7303 | 3.9159 | 2400 | 1.3201 | 0.2340 | 0.6187 |
| 0.793 | 4.2416 | 2600 | 1.3509 | 0.2305 | 0.6113 |
| 0.7757 | 4.5682 | 2800 | 1.3349 | 0.2367 | 0.6153 |
| 0.7047 | 4.8947 | 3000 | 1.3308 | 0.2323 | 0.6059 |
Framework versions
- Transformers 4.57.2
- Pytorch 2.9.1+cu128
- Datasets 3.6.0
- Tokenizers 0.22.0
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- wav2vec2
- License
- cc-by-nc-4.0
- Created
- Dec 5, 2025
- Updated
- Dec 5, 2025