21–30 of 99 posts
Any idea what the training data for this is? Looking at the model, it looks like it is literally just copy-paste from Karpathy's nanoGPT, so the training data is what's most interesting. Pretty amazing anyway.
I found a secret demo page that shows in real time how they assess any sound file's mood swings along with number of detected laughs, coughs, etc. Guessing that ability is involved somehow.
Earlier quoted context omitted.
From the readme: >Bark has the capability to fully clone voices - including tone, pitch, emotion and prosody. The model also attempts to preserve music, ambient noise, etc. from input audio. However, to mitigate misuse of this technology, we limit the audio history prompts to a limited set of Suno-provided, fully synthetic options to choose from for each language. It's not immediately clear how the audio history prom…
history prompts are just unconditionally generated TTS from the same model. any of those can be used as history, but for convenience 10 are provided for each language (to generate things with consistent voices)
Text to speech was a natural playground for us to share with the community and get some feedback. Given that this model is a full GPT model, the text input is merely a guidance and the model can technically create any audio from scratch even without input text, aka hallucinations or audio continuation.
When used as a TTS model, it’s very different from the awesome high quality TTS models already available. It produces a wider range of audio – that could be a high quality studio recording of an actor or the same text leading to two people shouting in an argument at a noisy bar. Excited to see what the community can build and what we can learn for future products.
Please let us know with any feedback, or if you’re interested in working on this: bark@suno.ai
Hey, one of the Suno founders/creators of Bark here. Thanks for all the comments, we love seeing how we can improve things in the future. At Suno we work on audio foundation models, creating speech, music, sounds effects etc…. Text to speech was a natural playground for us to share with the community and get some feedback. Given that this model is a full GPT model, the text input is merely a guidance and the model ca…
Very cool. Side note: bark-gpt.com is already taken for a dog translator: "The world’s first AI powered, real-time communications tool between humans and their furry best friends."[0] I only know this because my law firm partner's name is Bark, and I wanted to automate some legal work and name the software "Bark GPT" after him. [0] https://www.bark-gpt.com/
Hey, one of the Suno founders/creators of Bark here. Thanks for all the comments, we love seeing how we can improve things in the future. At Suno we work on audio foundation models, creating speech, music, sounds effects etc…. Text to speech was a natural playground for us to share with the community and get some feedback. Given that this model is a full GPT model, the text input is merely a guidance and the model ca…
Amazing work so far! Do you have any sense about how difficult it would be to enable M1/M2 or CoreML support?
Earlier quoted context omitted.
history prompts are just unconditionally generated TTS from the same model. any of those can be used as history, but for convenience 10 are provided for each language (to generate things with consistent voices)
So the history prompts are collections of text/audio pairs?
Isn't this open source and can be easily removed or am I missing something?