Downloads · 30 days
6
16% of all-time downloads
wav2vec2-fleur-mms-batch6-epoch16-finetunning-4
Nachuwu/wav2vec2-fleur-mms-batch6-epoch16-finetunning-4
wav2vec2-fleur-mms-batch6-epoch16-finetunning-4 is a automatic speech recognition model from Nachuwu. 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
37
Public
Parameters
965M
46.3 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 4, 2023
- Updated
- Dec 5, 2023
- SHA
- 2416610f
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-fleur-mms-batch6-epoch16-finetunning-4
This model is a fine-tuned version of Nachuwu/wav2vec2-fleur-mms-batch6-epoch24-finetunning-3 on the audiofolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.9908
- Wer: 0.4688
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: 6
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- num_epochs: 16
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 6.0051 | 2.86 | 100 | 2.3991 | 0.6776 |
| 1.1733 | 5.71 | 200 | 1.0311 | 0.4930 |
| 0.9654 | 8.57 | 300 | 0.9807 | 0.4798 |
| 0.9125 | 11.43 | 400 | 0.9950 | 0.4696 |
| 0.9099 | 14.29 | 500 | 0.9908 | 0.4688 |
Framework versions
- Transformers 4.36.0.dev0
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- wav2vec2
- License
- cc-by-nc-4.0
- Created
- Dec 4, 2023
- Updated
- Dec 5, 2023