Downloads · 30 days
8
15% of all-time downloads
wav2vec2-base-960h-demo-google-colab
St4n/wav2vec2-base-960h-demo-google-colab
wav2vec2-base-960h-demo-google-colab is a automatic speech recognition model from St4n. Use it when you need speech turned into text. It is set up for transformers. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
55
Public
Repo size
755 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin378 MB · 100%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- License
- apache-2.0
- Model type
- wav2vec2
- Access
- Public
- Created
- Oct 9, 2023
- Updated
- Oct 9, 2023
- SHA
- 9b1d345b
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. -->
wav2vec2-base-960h-demo-google-colab
This model is a fine-tuned version of facebook/wav2vec2-base-960h on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1495
- Wer: 0.1503
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: 0.0001
- train_batch_size: 16
- 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: 1000
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 6.7708 | 0.42 | 200 | 3.3194 | 0.9999 |
| 3.0354 | 0.84 | 400 | 3.1933 | 0.9999 |
| 2.796 | 1.26 | 600 | 1.4082 | 0.7669 |
| 1.0912 | 1.68 | 800 | 0.8231 | 0.3675 |
| 0.6568 | 2.1 | 1000 | 0.3944 | 0.2863 |
| 0.4604 | 2.52 | 1200 | 0.3303 | 0.2421 |
| 0.3932 | 2.94 | 1400 | 0.2730 | 0.2103 |
| 0.3356 | 3.35 | 1600 | 0.2189 | 0.1789 |
| 0.3117 | 3.77 | 1800 | 0.2189 | 0.1688 |
| 0.2332 | 4.19 | 2000 | 0.1802 | 0.1563 |
| 0.2283 | 4.61 | 2200 | 0.1495 | 0.1503 |
Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- wav2vec2
- License
- apache-2.0
- Created
- Oct 9, 2023
- Updated
- Oct 9, 2023