Downloads · 30 days
5
11% of all-time downloads
outputs_finetune3
SergeyAdamyan/outputs_finetune3
outputs_finetune3 is a automatic speech recognition model from SergeyAdamyan. Use it when you need speech turned into text. It is set up for transformers.
should probably proofread and complete it, then remove this comment. --
All-time downloads
45
Public
Parameters
581M
44.1 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors2.3 GB · 100%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- Model type
- wav2vec2-bert
- Access
- Public
- Created
- Nov 24, 2025
- Updated
- Nov 24, 2025
- SHA
- f96d094e
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. -->
outputs_finetune3
This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2387
- Wer: 0.2914
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: 5e-06
- train_batch_size: 8
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 2
- total_train_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: 200
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.5914 | 0.5038 | 500 | 0.2818 | 0.3268 |
| 0.6093 | 1.0071 | 1000 | 0.2764 | 0.3277 |
| 0.5349 | 1.5108 | 1500 | 0.2637 | 0.3196 |
| 0.4888 | 2.0141 | 2000 | 0.2613 | 0.3225 |
| 0.5106 | 2.5179 | 2500 | 0.2611 | 0.3178 |
| 0.4188 | 3.0212 | 3000 | 0.2532 | 0.3118 |
| 0.4391 | 3.5249 | 3500 | 0.2512 | 0.3090 |
| 0.3455 | 4.0282 | 4000 | 0.2460 | 0.3037 |
| 0.3495 | 4.5320 | 4500 | 0.2469 | 0.3026 |
| 0.3506 | 5.0353 | 5000 | 0.2452 | 0.3042 |
| 0.349 | 5.5390 | 5500 | 0.2474 | 0.2990 |
| 0.3143 | 6.0423 | 6000 | 0.2429 | 0.3000 |
| 0.2866 | 6.5461 | 6500 | 0.2443 | 0.2976 |
| 0.3469 | 7.0494 | 7000 | 0.2420 | 0.2980 |
| 0.3379 | 7.5531 | 7500 | 0.2409 | 0.2948 |
| 0.3262 | 8.0564 | 8000 | 0.2379 | 0.2939 |
| 0.2955 | 8.5602 | 8500 | 0.2393 | 0.2913 |
| 0.333 | 9.0635 | 9000 | 0.2396 | 0.2919 |
| 0.3258 | 9.5673 | 9500 | 0.2387 | 0.2914 |
Framework versions
- Transformers 4.57.1
- Pytorch 2.9.1+cu128
- Datasets 4.4.1
- Tokenizers 0.22.1
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- wav2vec2-bert
- Created
- Nov 24, 2025
- Updated
- Nov 24, 2025