-
### Feature request
Add functionality to the `openai_dart` module within the LangChain library to support audio transcription. This feature would allow users to transcribe audio files using OpenAI's …
-
commit id: e58fe48d2ee99310ce2066005c5108ac86942ad4
步骤
```
git clone https://github.com/2noise/ChatTTS
cd ChatTTS
conda create -n chattts
conda activate chattts
pip install -r requirements.txt
…
-
Windows系统,提示NotImplementedError: cannot instantiate 'PosixPath' on your system
INFO:modules.enhance.enhancer.download:Downloading the model...
INFO:modules.enhance.enhancer.download:Repository alr…
-
For some reason IINA only plays back audio in mono now. I tried multiple commands but none work.
VLC, the system audio and other audio applications like Tidal work just fine.
Is this a bug? Cause…
-
## Description
The mtg-jamendo dataset contains multiple instances of duplicate audio files, which are bitwise exact copies but have different filenames. These duplicates might cause issues in applic…
-
Hello,
I was following a tutorial on sound quality measurements of psychoacoustic parameters with MOSQITO
(https://www.minidsp.com/applications/acoustic-measurements/psychoacoustic-measurements-w…
-
Fooyin should technically support Matroska files out of the box from FFMPEG, however Fooyin doesn't automatically consider .mka files as audio files.
Personally, I use it as it allows essentially a…
-
Hello im using rhasspy on uvuntu 24.04lts when i let rhasspy speak it doesnt work please help
AudioServerException: Command ‘[‘aplay’, ‘-q’, ‘-t’, ‘wav’]’ returned non-zero exit status 1.
-
# Task Name
Audio Super-Resolution / High-Frequency Band Reconstruction.
## Task Objective
Due to the constraint of transmission/storage/recording, the typical audio sampling rate is 8/16/24kHz. …
-
# Task Name
Audio Spatial Distance Prediction
## Task Objective
Audio Spatial Distance Prediction is a task that aims to predict spatial distance from the source of the sound based on the giv…