Spaces:
Sleeping
Sleeping
mrfakename
commited on
Commit
•
7ccf7c7
1
Parent(s):
3c4712d
Update app.py
Browse files
app.py
CHANGED
@@ -177,8 +177,6 @@ with gr.Blocks() as app:
|
|
177 |
gr.Markdown("""
|
178 |
# E2/F5 TTS
|
179 |
|
180 |
-
> Zero-shot voice cloning, supporting English & Chinese
|
181 |
-
|
182 |
This is an unofficial E2/F5 TTS demo. This demo supports the following TTS models:
|
183 |
|
184 |
* [E2-TTS](https://arxiv.org/abs/2406.18009) (Embarrassingly Easy Fully Non-Autoregressive Zero-Shot TTS)
|
@@ -188,6 +186,8 @@ This demo is based on the [F5-TTS](https://github.com/SWivid/F5-TTS) codebase, w
|
|
188 |
|
189 |
The checkpoints support English and Chinese.
|
190 |
|
|
|
|
|
191 |
**NOTE: Reference text will be automatically transcribed with Whisper if not provided. For best results, keep your reference clips short (<15s). Ensure the audio is fully uploaded before generating.**
|
192 |
""")
|
193 |
|
|
|
177 |
gr.Markdown("""
|
178 |
# E2/F5 TTS
|
179 |
|
|
|
|
|
180 |
This is an unofficial E2/F5 TTS demo. This demo supports the following TTS models:
|
181 |
|
182 |
* [E2-TTS](https://arxiv.org/abs/2406.18009) (Embarrassingly Easy Fully Non-Autoregressive Zero-Shot TTS)
|
|
|
186 |
|
187 |
The checkpoints support English and Chinese.
|
188 |
|
189 |
+
If you're having issues, try converting your reference audio to WAV or MP3, clipping it to 15s, and shortening your prompt. If you're still running into issues, please open a [community Discussion](https://huggingface.co/spaces/mrfakename/E2-F5-TTS/discussions).
|
190 |
+
|
191 |
**NOTE: Reference text will be automatically transcribed with Whisper if not provided. For best results, keep your reference clips short (<15s). Ensure the audio is fully uploaded before generating.**
|
192 |
""")
|
193 |
|