Downloads · 30 days
6
1% of all-time downloads
ying-tina/wav2vec2-base-timit-demo-colab-32-epochs50-earlystop
wav2vec2-base-timit-demo-colab-32-epochs50-earlystop is a automatic speech recognition model from ying-tina. 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. --
Downloads · 30 days
6
1% of all-time downloads
All-time downloads
424
Public
Repo size
1.1 GB
Likes
0
Public
Click a slice to open those files.
.bin378 MB · 100%
From the Hugging Face model README
This model is a fine-tuned version of facebook/wav2vec2-base on the None dataset. It achieves the following results on the evaluation set:
More information needed
More information needed
More information needed
The following hyperparameters were used during training:
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 3.4294 | 4.0 | 500 | 1.3397 | 0.8966 |
| 0.5848 | 8.0 | 1000 | 0.4931 | 0.4585 |
| 0.2323 | 12.0 | 1500 | 0.4781 | 0.4008 |
| 0.14 | 16.0 | 2000 | 0.4294 | 0.3806 |
| 0.1026 | 20.0 | 2500 | 0.5098 | 0.3663 |
| 0.0725 | 24.0 | 3000 | 0.4527 | 0.3568 |
| 0.058 | 28.0 | 3500 | 0.5208 | 0.3561 |