Downloads · 30 days
81
7% of all-time downloads
dvinagre/speecht5-finetuned-common-voice-13-0-euskera
speecht5-finetuned-common-voice-13-0-euskera is a text-to-speech model from dvinagre. Use it when you need text read aloud. It is set up for transformers. The card lists the license as mit.
should probably proofread and complete it, then remove this comment. --
Downloads · 30 days
81
7% of all-time downloads
All-time downloads
1.2K
Public
Parameters
146M
2.9 GB on disk
Likes
0
Public
Click a slice to open those files.
.bin585 MB · 50%
From the Hugging Face model README
This model is a fine-tuned version of microsoft/speecht5_tts on the Common Voice 13 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 |
|---|---|---|---|
| 0.5624 | 3.26 | 1000 | 0.5073 |
| 0.5223 | 6.51 | 2000 | 0.4824 |
| 0.5197 | 9.77 | 3000 | 0.4768 |
| 0.5071 | 13.02 | 4000 | 0.4667 |