Downloads · 30 days
79
10% of all-time downloads
Avitas8485/speecht5_tts_commonvoice_en_05
speecht5_tts_commonvoice_en_05 is a text-to-speech model from Avitas8485. 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
79
10% of all-time downloads
All-time downloads
776
Public
Parameters
144M
7.5 GB on disk
Likes
0
Public
Click a slice to open those files.
.bin578 MB · 50%
From the Hugging Face model README
This model is a fine-tuned version of Avitas8485/speecht5_tts_commonvoice_en_04 on the ljspeech 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 |
|---|---|---|---|
| 0.4078 | 1.36 | 1000 | 0.3700 |
| 0.3981 | 2.71 | 2000 | 0.3680 |
| 0.4026 | 4.07 | 3000 | 0.3666 |
| 0.4026 | 5.43 | 4000 | 0.3664 |