Spaces:
Running
Running
seriar
commited on
Commit
•
bebc984
1
Parent(s):
eb73539
doc: fix examples in README
Browse files- make instructions on what to download from Releases more precise
- add `--speaker_id` argument with one of the speakers
README.md
CHANGED
|
@@ -49,12 +49,13 @@ https://user-images.githubusercontent.com/5759207/190852270-7aed2db9-dc08-4a9f-8
|
|
| 49 |
|
| 50 |
# How to use:
|
| 51 |
1. `pip install -r requirements.txt`.
|
| 52 |
-
2. Download model from "Releases" tab.
|
| 53 |
3. Launch as one-time command:
|
| 54 |
```
|
| 55 |
tts --text "Text for TTS" \
|
| 56 |
--model_path path/to/model.pth \
|
| 57 |
--config_path path/to/config.json \
|
|
|
|
| 58 |
--out_path folder/to/save/output.wav
|
| 59 |
```
|
| 60 |
or alternatively launch web server using:
|
|
|
|
| 49 |
|
| 50 |
# How to use:
|
| 51 |
1. `pip install -r requirements.txt`.
|
| 52 |
+
2. Download `model.pth` and `speakers.pth` from "Releases" tab.
|
| 53 |
3. Launch as one-time command:
|
| 54 |
```
|
| 55 |
tts --text "Text for TTS" \
|
| 56 |
--model_path path/to/model.pth \
|
| 57 |
--config_path path/to/config.json \
|
| 58 |
+
--speaker_idx dmytro \
|
| 59 |
--out_path folder/to/save/output.wav
|
| 60 |
```
|
| 61 |
or alternatively launch web server using:
|