midashenglm-gen

LLM‑driven autoregressive flow matching for unified speech‑music‑sound‑effect audio scene generation

xiaomi-research/midashenglm-gen

View on GitHub ↗

LLM‑driven autoregressive flow matching for unified speech‑music‑sound‑effect audio scene generation

midashenglm-gen grew +0.0% in the last 30 days, ranks 78th of 79 in Audio / Speech Models, last commit 101 days ago.

Star trajectory

82 days tracked
2026-08-31101 stars today2026-11-22
Momentum

+0.0% in 30d, below the Audio / Speech Models median of +0.2%.

Maintenance

Last commit 101 days ago, fresher than the median of 277d.

How it compares in Audio / Speech Models

midashenglm-gen
101
stars
+0.0% 30d
commit 101 days ago
Audio / Speech Models median
1.7k
stars
+0.2% 30d
commit ~277d ago
Leader · GPT-SoVITS
64.2k
stars
+1.0% 30d
commit 10 days ago

Ranked 78th of 79 by stars.

Ranked by shared tags, then keywords, then stars
  1. The collection of pre-trained, state-of-the-art AI models for ailia SDK

    +3 (+0.1%) in 30d · Committed 2d ago · Python · Other license

    Shares Vision & Multimodal Models, Audio / Speech Models

  2. Vector Hub - Library for easy discovery, and consumption of State-of-the-art models to turn data into vectors…

    +1 (+0.2%) in 30d · Committed 824d ago

    Shares Vision & Multimodal Models, Audio / Speech Models

  3. DuplexJev-32B and DuplexJev-4B: speech decision models for full-duplex voice agents. Typed single-token…

    Committed 14d ago · Python · Apache-2.0

    Shares Audio / Speech Models, Vision & Multimodal Models

  4. Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.

    +377 (+1.6%) in 30d · Committed 180d ago · Python · Apache-2.0

    Shares Audio / Speech Models

  5. A text-to-speech (TTS), speech-to-text (STT) and speech-to-speech (STS) library built on Apple's MLX…

    +227 (+2.8%) in 30d · Committed yesterday · Python · MIT

    Shares Audio / Speech Models

  6. StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and Adversarial Training with Large…

    +13 (+0.2%) in 30d · Committed 834d ago · Python · MIT

    Shares Audio / Speech Models

  7. AuK: An Open-Source Foundational Model for Speech Generation and Editing

    +77 (+5.0%) in 30d · Committed 2d ago · Python · Other license

    Shares Audio / Speech Models

  8. A multilingual model for long-form, multi-speaker dialogue synthesis with flexible speaker control and…

    +13 (+0.9%) in 30d · Committed 77d ago · Python · Apache-2.0

    Shares Audio / Speech Models

  9. Confucius4-TTS: a Multilingual and Cross-Lingual Zero-Shot TTS Engine

    +15 (+1.8%) in 30d · Committed 17d ago · Python · Other license

    Shares Audio / Speech Models

  10. An implementation of Tacotron 2 that supports multilingual experiments with parameter-sharing, code-switching…

    +0 (+0.0%) in 30d · Committed 1,138d ago · Python · MIT

    Shares Audio / Speech Models

Language
Python
License
Apache License 2.0
Contributors
1
Forks
8
Watchers
1
Open issues
1
Releases
0
Created
2026-08-11
Stars this week
+0

You've seen where midashenglm-gen stands today.

Get the moves before everyone else: the 5 Audio / Speech Models repos climbing fastest, every Tuesday.

Free weekly digest. Double opt-in, unsubscribe anytime.

Maintain midashenglm-gen?

Claim this page to add your own call-to-action.

Claim this page