Commit
•
4dda3a2
1
Parent(s):
0bc5779
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,25 @@
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
|
|
|
|
|
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
| 3 |
+
language:
|
| 4 |
+
- de
|
| 5 |
---
|
| 6 |
+
|
| 7 |
+
# "Thorsten-Voice" TTS Modell (neutral) - Tacotron2 DDC
|
| 8 |
+
Dieses Modell wurde auf Basis von Coqui TTS trainiert.
|
| 9 |
+
|
| 10 |
+
# Dateien
|
| 11 |
+
## TTS Modell
|
| 12 |
+
* tts-config.json
|
| 13 |
+
* tts-config.json
|
| 14 |
+
|
| 15 |
+
## Vocoder Modell (HifiGAN v1)
|
| 16 |
+
* scale_stats.npy
|
| 17 |
+
* vocoder-config.json
|
| 18 |
+
* vocoder-model_file.pth.tar
|
| 19 |
+
|
| 20 |
+
# Nutzung
|
| 21 |
+
Das Coqui TTS Paket installieren.
|
| 22 |
+
> pip install tts -U
|
| 23 |
+
|
| 24 |
+
Dann den lokalen TTS-Server Prozess starten:
|
| 25 |
+
> tts-server --model_path tts-model_file.pth --config_path tts-config.json --vocoder_path vocoder-model_file.pth.tar --vocoder_config_path vocoder-config.json
|