Downloads · 30 days
12
44% of all-time downloads
wav2vec2-large-mms-1b-aft-ttj
robertp408/wav2vec2-large-mms-1b-aft-ttj
wav2vec2-large-mms-1b-aft-ttj 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
27
Public
Parameters
965M
139 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 29, 2025
- Updated
- Oct 8, 2025
- SHA
- 3349defa
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-ttj
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: 0.1910
- Wer: 0.2713
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 |
|---|---|---|---|---|
| 7.617 | 0.1393 | 100 | 5.0059 | 1.0027 |
| 4.88 | 0.2786 | 200 | 4.0449 | 1.0 |
| 3.5904 | 0.4178 | 300 | 2.9475 | 1.0 |
| 2.135 | 0.5571 | 400 | 0.3999 | 0.5100 |
| 0.4686 | 0.6964 | 500 | 0.2951 | 0.4108 |
| 0.3908 | 0.8357 | 600 | 0.2649 | 0.3752 |
| 0.3717 | 0.9749 | 700 | 0.2556 | 0.3548 |
| 0.3491 | 1.1142 | 800 | 0.2481 | 0.3394 |
| 0.3317 | 1.2535 | 900 | 0.2407 | 0.3325 |
| 0.3823 | 1.3928 | 1000 | 0.2364 | 0.3248 |
| 0.3441 | 1.5320 | 1100 | 0.2250 | 0.3092 |
| 0.3515 | 1.6713 | 1200 | 0.2207 | 0.3110 |
| 0.3767 | 1.8106 | 1300 | 0.2237 | 0.3113 |
| 0.3137 | 1.9499 | 1400 | 0.2164 | 0.2990 |
| 0.3348 | 2.0891 | 1500 | 0.2173 | 0.3100 |
| 0.2845 | 2.2284 | 1600 | 0.2157 | 0.3014 |
| 0.3221 | 2.3677 | 1700 | 0.2149 | 0.2991 |
| 0.2798 | 2.5070 | 1800 | 0.2094 | 0.2903 |
| 0.2822 | 2.6462 | 1900 | 0.2094 | 0.3024 |
| 0.3066 | 2.7855 | 2000 | 0.2064 | 0.2915 |
| 0.3252 | 2.9248 | 2100 | 0.2066 | 0.2989 |
| 0.2793 | 3.0641 | 2200 | 0.2100 | 0.2988 |
| 0.3247 | 3.2033 | 2300 | 0.2043 | 0.2928 |
| 0.266 | 3.3426 | 2400 | 0.1999 | 0.2789 |
| 0.2718 | 3.4819 | 2500 | 0.2000 | 0.2761 |
| 0.3037 | 3.6212 | 2600 | 0.2010 | 0.2847 |
| 0.2663 | 3.7604 | 2700 | 0.1950 | 0.2730 |
| 0.2641 | 3.8997 | 2800 | 0.1957 | 0.2762 |
| 0.2503 | 4.0390 | 2900 | 0.1933 | 0.2704 |
| 0.2356 | 4.1783 | 3000 | 0.1948 | 0.2759 |
| 0.2681 | 4.3175 | 3100 | 0.1931 | 0.2702 |
| 0.2694 | 4.4568 | 3200 | 0.1918 | 0.2685 |
| 0.2545 | 4.5961 | 3300 | 0.1930 | 0.2696 |
| 0.2659 | 4.7354 | 3400 | 0.1913 | 0.2719 |
| 0.2235 | 4.8747 | 3500 | 0.1910 | 0.2713 |
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 29, 2025
- Updated
- Oct 8, 2025