Downloads · 30 days
5
13% of all-time downloads
wav2vec2-base-timit-demo-colab_2
fahadtouseef/wav2vec2-base-timit-demo-colab_2
wav2vec2-base-timit-demo-colab_2 is a automatic speech recognition model from fahadtouseef. 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
40
Public
Repo size
1.1 GB
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
- May 2, 2022
- Updated
- May 2, 2022
- SHA
- 6d34a47e
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-timit-demo-colab_2
This model is a fine-tuned version of facebook/wav2vec2-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3801
- Wer: 0.3035
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: 30
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 4.7227 | 3.52 | 500 | 2.6961 | 1.0 |
| 1.1237 | 7.04 | 1000 | 0.6088 | 0.5315 |
| 0.4886 | 10.56 | 1500 | 0.4709 | 0.4353 |
| 0.3148 | 14.08 | 2000 | 0.4341 | 0.3942 |
| 0.2229 | 17.61 | 2500 | 0.4035 | 0.3616 |
| 0.1693 | 21.13 | 3000 | 0.3868 | 0.3289 |
| 0.1393 | 24.65 | 3500 | 0.3993 | 0.3135 |
| 0.118 | 28.17 | 4000 | 0.3801 | 0.3035 |
Framework versions
- Transformers 4.11.3
- Pytorch 1.11.0+cu113
- Datasets 1.18.3
- Tokenizers 0.10.3
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- wav2vec2
- License
- apache-2.0
- Created
- May 2, 2022
- Updated
- May 2, 2022