OpenBMB / OpenBMB/VoxCPM

Replacing LM(MiniCPM4) with MiniCPM-SALA

Open
#193 7 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
37.8k
Forks
4.3k
Avg merge
7m
Merged PRs (30d)
1

Description

Hey! I was wondering if we can scale the LM from 0.5B to 8B version, specially the SALA version which is optimised for inference and quicker trainings. The expressivity and naturalness should go up sharply.

Since, the pre-training data is not open-source, and there is very limited 44/48 kHz data available, I was wondering how this can be done?

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

The issue names no files, tests, or entry points. Start by locating the current LM(MiniCPM4) integration and reviewing how the model depends on available pre-training and 44/48 kHz data. Done means establishing whether MiniCPM-SALA can replace it and defining the implementation and data requirements.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Quiet
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.