[Docs] Add Stable Audio Open text-to-audio recipe#193
Conversation
Summary of ChangesHello @linyueqian, I'm Gemini Code Assist1! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed! This pull request introduces a comprehensive documentation file that serves as a guide for integrating and utilizing the Stable Audio Open text-to-audio model with vLLM-Omni. The guide provides clear instructions for setting up the environment, generating audio through both programmatic and command-line interfaces, and understanding the model's capabilities and constraints. Highlights
🧠 New Feature in Public Preview: You can now enable Memory to help Gemini Code Assist learn from your team's feedback. This makes future code reviews more consistent and personalized to your project's style. Click here to enable Memory in your admin console. Using Gemini Code AssistThe full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips. Invoking Gemini You can request assistance from Gemini at any point by creating a comment using either
Customization To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a Limitations & Feedback Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here. You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension. Footnotes
|
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
There was a problem hiding this comment.
Code Review
This pull request introduces a new usage guide for Stable Audio Open with vLLM-Omni. The guide is well-written and provides valuable information for users. I've included a couple of suggestions to correct an installation command and improve clarity.
To ensure users can find this new guide, please also add a link to it in the main README.md file. You could add a new section for 'Stability AI' similar to how other models are listed.
| |-----------|---------|-------------| | ||
| | `audio_start_in_s` | 0.0 | Audio start time in seconds | | ||
| | `audio_end_in_s` | 10.0 | Audio end time in seconds | | ||
| | `audio_length` | 10.0 | Audio duration (CLI convenience, sets end time) | |
There was a problem hiding this comment.
The description for audio_length could be more specific. To improve clarity for users, I suggest explicitly mentioning that it sets the audio_end_in_s parameter.
| | `audio_length` | 10.0 | Audio duration (CLI convenience, sets end time) | | |
| | `audio_length` | 10.0 | Audio duration in seconds (CLI convenience). Sets `audio_end_in_s` to this value. | |
| ### Saving Audio Output | ||
|
|
||
| ```python | ||
| import numpy as np | ||
| import soundfile as sf | ||
|
|
||
| # Convert to numpy if needed | ||
| if isinstance(audio, torch.Tensor): | ||
| audio = audio.cpu().float().numpy() | ||
|
|
||
| # Audio shape is [batch, channels, samples] | ||
| audio_data = audio[0].T # [samples, channels] | ||
| sf.write("output.wav", audio_data, 44100) | ||
| ``` |
There was a problem hiding this comment.
I think this part can cosolidate with Basic Usage above.
There was a problem hiding this comment.
got it i have updated it.
Co-authored-by: Isotr0py <2037008807@qq.com> Signed-off-by: Yueqian Lin <70319226+linyueqian@users.noreply.github.com>
Signed-off-by: Yueqian Lin <70319226+linyueqian@users.noreply.github.com> Co-authored-by: Isotr0py <2037008807@qq.com>
Signed-off-by: Yueqian Lin <70319226+linyueqian@users.noreply.github.com> Co-authored-by: Isotr0py <2037008807@qq.com> Signed-off-by: haic0 <hc@XSZAEAIHC02.amd.com>
Signed-off-by: Yueqian Lin <70319226+linyueqian@users.noreply.github.com> Co-authored-by: Isotr0py <2037008807@qq.com> Signed-off-by: haic0 <hc@XSZAEAIHC02.amd.com>
2 participants
No description provided.