Skip to content

Commit 88d41af

Browse files
authoredJan 19, 2024
Fix USAGE.md links
Fix `demo_part1.ipynb` and `demo_part2.ipynb` link
1 parent 2e55e77 commit 88d41af

File tree

1 file changed

+3
-3
lines changed

1 file changed

+3
-3
lines changed
 

‎docs/USAGE.md

+3-3
Original file line numberDiff line numberDiff line change
@@ -42,15 +42,15 @@ pip install -r requirements.txt
4242
Download the checkpoint from [here](https://myshell-public-repo-hosting.s3.amazonaws.com/checkpoints_1226.zip) and extract it to the `checkpoints` folder
4343

4444
**1. Flexible Voice Style Control.**
45-
Please see [`demo_part1.ipynb`](demo_part1.ipynb) for an example usage of how OpenVoice enables flexible style control over the cloned voice.
45+
Please see [`demo_part1.ipynb`](../demo_part1.ipynb) for an example usage of how OpenVoice enables flexible style control over the cloned voice.
4646

4747
**2. Cross-Lingual Voice Cloning.**
48-
Please see [`demo_part2.ipynb`](demo_part2.ipynb) for an example for languages seen or unseen in the MSML training set.
48+
Please see [`demo_part2.ipynb`](../demo_part2.ipynb) for an example for languages seen or unseen in the MSML training set.
4949

5050
**3. Gradio Demo.**. We provide a minimalist local gradio demo here. We strongly suggest the users to look into `demo_part1.ipynb`, `demo_part2.ipynb` and the [QnA](QA.md) if they run into issues with the gradio demo. Launch a local gradio demo with `python -m openvoice_app --share`.
5151

5252
**3. Advanced Usage.**
5353
The base speaker model can be replaced with any model (in any language and style) that the user prefer. Please use the `se_extractor.get_se` function as demonstrated in the demo to extract the tone color embedding for the new base speaker.
5454

5555
**4. Tips to Generate Natural Speech.**
56-
There are many single or multi-speaker TTS methods that can generate natural speech, and are readily available. By simply replacing the base speaker model with the model you prefer, you can push the speech naturalness to a level you desire.
56+
There are many single or multi-speaker TTS methods that can generate natural speech, and are readily available. By simply replacing the base speaker model with the model you prefer, you can push the speech naturalness to a level you desire.

0 commit comments

Comments
 (0)
Please sign in to comment.