open-musiclm
audiocraft-infinity-webui
open-musiclm | audiocraft-infinity-webui | |
---|---|---|
1 | 2 | |
482 | 152 | |
- | - | |
7.0 | 7.5 | |
12 months ago | 9 months ago | |
Python | Python | |
MIT License | GNU Affero General Public License v3.0 |
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.
open-musiclm
-
[Research] Pretrained MusicLM?
I'm working on a personal project where I'm planning to create a fine-tuned version of Music LM, but I'm not sure if there are any pretrained weights that I can use that are available to the public. The closest thing that I can find is this: GitHub - zhvng/open-musiclm: Implementation of MusicLM, a text to music model published by Google Research, with a few modifications.which is a modified, custom version of MusicLM, but I'm looking for something closer to the paper. Does anyone have any resources on this?
audiocraft-infinity-webui
-
Audiocraft Infinity Webui MusicGen training - help
I'm using the https://github.com/1aienthusiast/audiocraft-infinity-webui repo to train the model on my music. However, when I use the fine-tuned model to generate audio, it comes out as a big mess of sounds and noise.
-
Longer than 30 sec?
I've used audiocraft-infinity-webui for this, and it actually works surprisingly well. Some longer tracks might be hit-or-miss and require several attempts, but I've gotten it to produce coherent 5-minute-long tracks.
What are some alternatives?
Los-Angeles-Music-Composer - Local windowed attention multi-instrumental music transformer for supervised music generation
MidiTok - MIDI / symbolic music tokenizers for Deep Learning models 🎶
Lars-Ulrich-Challenge - Algorithmic and AI MIDI Drums Generator Implementation
audiocraft - 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.
Perceiver - Implementation of Perceiver, General Perception with Iterative Attention in TensorFlow
tuneflow-py - 🧠+🎧 Build your music algorithms and AI models with the next-gen DAW 🔥
namekrea - NameKrea is an AI Domain Name Generator which uses GPT-2