Downloads · 30 days
6
26% of all-time downloads
wav2vec2-large-mms-1b-aft-sco
robertp408/wav2vec2-large-mms-1b-aft-sco
wav2vec2-large-mms-1b-aft-sco 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
23
Public
Parameters
965M
50.2 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
- Sep 27, 2025
- Updated
- Oct 8, 2025
- SHA
- f4d0a6e9
Base models
Datasets
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. -->
wav2vec2-large-mms-1b-aft-sco
This model is a fine-tuned version of facebook/mms-1b-all on the audiofolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.4899
- Wer: 0.3626
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: 2
- eval_batch_size: 8
- seed: 42
- 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 | Wer |
|---|---|---|---|---|
| 5.7299 | 0.4717 | 100 | 3.2165 | 0.9977 |
| 1.9086 | 0.9434 | 200 | 0.7009 | 0.4424 |
| 0.595 | 1.4151 | 300 | 0.5888 | 0.4184 |
| 0.5914 | 1.8868 | 400 | 0.5640 | 0.3986 |
| 0.4985 | 2.3585 | 500 | 0.5354 | 0.3833 |
| 0.5175 | 2.8302 | 600 | 0.5203 | 0.3816 |
| 0.4826 | 3.3019 | 700 | 0.5103 | 0.3735 |
| 0.4726 | 3.7736 | 800 | 0.5035 | 0.3668 |
| 0.4319 | 4.2453 | 900 | 0.4946 | 0.3654 |
| 0.4316 | 4.7170 | 1000 | 0.4899 | 0.3626 |
Framework versions
- Transformers 4.57.0
- Pytorch 2.8.0+cu128
- Datasets 4.1.1
- Tokenizers 0.22.1
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- wav2vec2
- License
- cc-by-nc-4.0
- Created
- Sep 27, 2025
- Updated
- Oct 8, 2025