-
# Task Name: Text-to-Audio Generation
The task aims to generate general audio based on the given holistic text description.
## Task Objective
The primary goal of the Text-to-Sound (TTA) Gener…
-
### Is it an issue related to Adaptive Cards?
No.
### What is the PWD impact?
### User Experience:
Transcript or captions should be provided for the video only or audio only content so that it is e…
-
The rebrowser patches is great and i am sure there is a lot difference now from any puppeteer versions. What i found was like once we open a browser and type something it works perfect but trying to a…
-
Unrecognized model in D:\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\ComfyUI\models\Joy_caption_two\text_model. Should have a `model_type` key in its config.json, or contain one of the fo…
-
### Describe the bug
I have upgraded to version 3.13.0 and the error persists when deleting messages (audio, video, image, text).
1. In case of audios that I delete from Instagram or Facebook websi…
-
When I try and run `app.py` under `Intelligent MIDI Comparator Gradio App` I get the error
```
Traceback (most recent call last):
File "D:\Tests\Giant Music Transformer\Giant-Music-Transformer\…
-
### Description
I'm not actually sure if it's my fault, but when i try to call the audio endpoints (like enumAudioEndpoints, getDefaultAudioEndpoint, getDevice), my app crash.
### Steps To Repro…
-
## Inspiration
So there is a gradio space [https://huggingface.co/spaces/hf-audio/whisper-large-v3](url) that uses whisper, from the hugging face api :
```python
import spaces
import torch
…
240db updated
1 month ago
-
Would it be possible to release these reports as markdown text first with a PDF version derived from it?
While it's useful to have the PDFs version-controlled via git, because PDF is a binary forma…
-
For Debian we have a speech variant of the installer. It will run a screen reader during the installation steps.
It is possible to capture the audio, but it will take a lot longer to speak all text…