Downloads · 30 days
2
7% of all-time downloads
ntsema/wav2vec2-xlsr-53-espeak-cv-ft-mhr4-ntsema-colab
wav2vec2-xlsr-53-espeak-cv-ft-mhr4-ntsema-colab is a automatic speech recognition model from ntsema. 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
2
7% of all-time downloads
All-time downloads
29
Public
Repo size
3.8 GB
Likes
0
Public
Click a slice to open those files.
.bin1.3 GB · 100%
From the Hugging Face model README
This model is a fine-tuned version of facebook/wav2vec2-xlsr-53-espeak-cv-ft on the audiofolder 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 |
|---|---|---|---|---|
| 4.4262 | 5.19 | 400 | 3.4455 | 0.9565 |
| 1.3573 | 10.39 | 800 | 1.4851 | 0.7826 |
| 0.8157 | 15.58 | 1200 | 0.9671 | 0.4783 |
| 0.5221 | 20.78 | 1600 | 0.7426 | 0.4130 |
| 0.3465 | 25.97 | 2000 | 0.8884 | 0.3478 |