mirror of
https://github.com/AIGC-Audio/AudioGPT.git
synced 2025-12-15 19:37:52 +01:00
update
This commit is contained in:
@@ -66,13 +66,8 @@ Input Example : Please tell me the text description of this audio.<br />
|
||||
Output:<br />
|
||||
<br />
|
||||
|
||||
## Image
|
||||
### Text-To-Image
|
||||
Input Example : Generate an image of a horse<br />
|
||||
Output:<br />
|
||||
<br />
|
||||
|
||||
## Sound Detection
|
||||
### Sound Detection
|
||||
First upload your audio(.wav)<br />
|
||||
Audio Example :<br />
|
||||
<audio src="mix.wav" controls></audio><br />
|
||||
@@ -80,21 +75,21 @@ Input Example : What events does this audio include?<br />
|
||||
Output:<br />
|
||||
<br />
|
||||
|
||||
## Mono audio to Binaural Audio
|
||||
### Mono audio to Binaural Audio
|
||||
First upload your audio(.wav)<br />
|
||||
<audio src="mix.wav" controls></audio><br />
|
||||
Input Example: Transfer the mono speech to a binaural one audio.<br />
|
||||
Output:<br />
|
||||
<br />
|
||||
|
||||
## Target Sound Detection
|
||||
### Target Sound Detection
|
||||
Fisrt upload your audio(.wav)<br />
|
||||
<audio src="mix.wav" controls></audio><br />
|
||||
Input Example: please help me detect the target sound in the audio based on desription: “I want to detect Applause event”<br />
|
||||
Output:<br />
|
||||
<br />
|
||||
|
||||
## Sound Extraction
|
||||
### Sound Extraction
|
||||
First upload your audio(.wav)<br />
|
||||
<audio src="mix.wav" controls></audio><br />
|
||||
Input Example: Please help me extract the sound events from the audio based on the description: "a person shouts nearby and then emergency vehicle sirens sounds"<br />
|
||||
|
||||
Reference in New Issue
Block a user