bark
audio-webui
bark | audio-webui | |
---|---|---|
67 | 15 | |
32,784 | 908 | |
3.8% | - | |
5.4 | 9.0 | |
8 days ago | 25 days ago | |
Jupyter Notebook | Python | |
MIT License | MIT License |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
bark
-
Exploring Bark, the Open Source Text-to-Speech Model
!pip install git+https://github.com/suno-ai/bark.git
-
AI-generated sad girl with piano performs the text of the MIT License
To my knowledge, the model being used for this is "chirp" which is 'based on' bark[1], an AI text to speech model.
The github page for bark links to a page about chirp, which returns a 404 page for me [2]. that the model for suno.ai's song generator isn't too much different than the text to speech model.
My hunch is that it was something like a coincidence that the bark model was capable of producing music, and that was spun off into this product. Unfortunately, there seems to still be issues with bark when generating long (like book length) spoken audio. Which is too bad, as someone who's worked jobs that require lots of driving, it would be awesome to be able to have any text read to me in a natural sounding voice.
[1]https://github.com/suno-ai/bark
-
Generating music in the waveform domain (2020)
Stable-audio and MusicGen sounds better than Jukebox.
But the best so far is Suno.ai ( https://app.suno.ai ) especially with their V3 model they have very impressive results, the fidelity is not studio quality but they're getting very close.
It's very likely based on their TTS model they have released before Bark, but trained on more data and with higher resolution.
https://github.com/suno-ai/bark
-
Stable-Audio-Demo
https://github.com/suno-ai/bark
> Bark was developed for research purposes. It is not a conventional text-to-speech model but instead a fully generative text-to-audio model, which can deviate in unexpected ways from provided prompts. Suno does not take responsibility for any output generated. Use at your own risk, and please act responsibly.
I've generated probably >200 songs now with Suno, of which perhaps 10 have been any good, and I can't detect any pattern in terms of the outputs.
Here's another one which is pretty good. I accidentally copied and pasted the prompt and lyrics, and it's amazing to me how 'musically' it renders the prompt:
-
Suno AI
hahah wow! cool :-)
PS: OT, I am reading this Bark thing(https://github.com/suno-ai/bark). Can I run it locally on a Macbook 2015 with 8GB RAM?
-
SDXL + SVD + Suno AI
I have it locally. The model is on huggingface. It runs with about 8GB VRAM.
- [discussion] text to voice generation for textbooks
-
Open Source Libraries
suno-ai/bark
- Weird A.I. Yankovic, a cursed deep dive into the world of voice cloning
- FLaNK Stack Weekly 2 October 2023
audio-webui
-
Sub for AI voice models
I mean, just use gitmylo's repo.
-
What are some good tools for text2audio that I can run locally?
For pure voice and not autogeneration from the LLM you have stuff like: https://github.com/gitmylo/audio-webui
-
Open Source Libraries
gitmylo/audio-webui
-
Dedicated Riffusion Gradio training interface?
I was wondering if there might be some way to incorporate Riffusion and it's various capabilities into this platform? Multiple attempts have been made by me on my local server to combine the Automatic111 SD-Web-UI extensions and such into the Audiocraft_Plus (https://github.com/GrandaddyShmax/audiocraft_plus) and Audio Web (https://github.com/gitmylo/audio-webui) Ui's platform, but truth be told I am a total beginner and keep coming up short!
-
Any local voice models?
audio-webui is the stable diffusion of txt 2 speech stuff but don't expect high quality voice replication for a while. https://github.com/gitmylo/audio-webui
-
Best Tool for creating an AI celebrity voice clone?
You can try Audio-Webui if you're technically savvy. There are some voice cloning workflows as well as RVC, voice conversion.
-
Are there any AI resources to help create audiobooks from text to speech?
Have not tested but it looks like the audio-webui repo is ready for long texts (just click the COLAB link to test it). I would test it and then go tortoise if the quality is not as needed.
-
I found a youtube tutorial voiceover made by AI, and I'm blown away by its quality. Can you help me figure out which tool did the author use?
This is the best open source voice cloning. Super easy to install also.
-
How to change your voice to someone else’s for a song? What are the best ways being used right now?
People use https://github.com/gitmylo/audio-webui and https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI for that Check out this tutorial : https://www.youtube.com/watch?v=-JcvdDErkAU It's possible to separate music or background noises from voice with these tech and recombine them together or with other songs, it's amazing and fun.
-
What would be the Stable Diffusion equivalent, for AI music generation?
Check this out : https://github.com/gitmylo/audio-webui/wiki/Features
What are some alternatives?
tortoise-tts - A multi-voice TTS system trained with an emphasis on quality
SadTalker - [CVPR 2023] SadTalker:Learning Realistic 3D Motion Coefficients for Stylized Audio-Driven Single Image Talking Face Animation
TTS - 🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production
Retrieval-based-Voice-Conversion-WebUI - Easily train a good VC model with voice data <= 10 mins!
audiocraft_plus - Audiocraft is a library for audio processing and generation with deep learning. It features the state-of-the-art EnCodec audio compressor / tokenizer, along with MusicGen, a simple and controllable music generation LM with textual and melodic conditioning.
whisper.cpp - Port of OpenAI's Whisper model in C/C++
DeepFilterNet - Noise supression using deep filtering
text-generation-webui - A Gradio web UI for Large Language Models. Supports transformers, GPTQ, AWQ, EXL2, llama.cpp (GGUF), Llama models.
bark-voice-cloning-HuBERT-quantizer - The code for the bark-voicecloning model. Training and inference.