Skip to content
Navigation Menu
Sign in
Appearance settings
Platform
AI CODE CREATION
GitHub Copilot
Write better code with AI
GitHub Copilot app
Direct agents from issue to merge
MCP Registry
Integrate external tools
DEVELOPER WORKFLOWS
Actions
Automate any workflow
Codespaces
Instant dev environments
Issues
Plan and track work
Code Review
Manage code changes
Code Quality
Enforce quality at merge
APPLICATION SECURITY
GitHub Advanced Security
Find and fix vulnerabilities
Code security
Secure your code as you build
Secret protection
Stop leaks before they start
EXPLORE
Why GitHub
Documentation
Blog
Changelog
Marketplace
View all features
Solutions
BY COMPANY SIZE
Enterprises
Small and medium teams
Startups
Nonprofits
BY USE CASE
App Modernization
DevSecOps
DevOps
CI/CD
View all use cases
BY INDUSTRY
Healthcare
Financial services
Manufacturing
Government
View all industries
View all solutions
Resources
EXPLORE BY TOPIC
AI
Software Development
DevOps
Security
View all topics
EXPLORE BY TYPE
Customer stories
Events & webinars
Ebooks & reports
Business insights
GitHub Skills
SUPPORT & SERVICES
Documentation
Customer support
Community forum
Trust center
Partners
View all resources
Open Source
COMMUNITY
GitHub Sponsors
Fund open source developers
PROGRAMS
Security Lab
Maintainer Community
GitHub Stars
Archive Program
REPOSITORIES
Topics
Trending
Collections
Enterprise
ENTERPRISE SOLUTIONS
Enterprise platform
AI-powered developer platform
AVAILABLE ADD-ONS
GitHub Advanced Security
Enterprise-grade security features
Copilot for Business
Enterprise-grade AI features
Premium Support
Enterprise-grade 24/7 support
Pricing
Search
/
Sign in
Sign up
Appearance settings
You signed in with another tab or window.
Reload
to refresh your session.
You signed out in another tab or window.
Reload
to refresh your session.
You switched accounts on another tab or window.
Reload
to refresh your session.
Dismiss alert
{{ message }}
NairoDorian
speech.cpp
Repository navigation
Code
Pull requests
Actions
Projects
Security and quality
Insights
More
items
Commits
Breadcrumbs
History for
speech.cpp
src
framework
on
main
User selector
All users
Datepicker
All time
Commit history
Commits on Sep 26, 2026
wip(engine): Phase 11b port batch + quick/full test tiers (verdicts NOT green)
Show description for d6d4f27
NairoDorian
and
claude
committed
d6d4f27
View commit details
Copy full SHA for d6d4f27
View code at this point
Browse repository at this point
Commits on Sep 23, 2026
fix(engine): keep once-uploaded graph constants alive across cached-graph reuse (21 sites)
Show description for d04fd55
NairoDorian
and
claude
committed
d04fd55
View commit details
Copy full SHA for d04fd55
View code at this point
Browse repository at this point
merge: reconcile upstream audio.cpp@main (9bdd1d90, v0.8.2, 70 commits)
Show description for 38769d5
NairoDorian
and
claude
committed
38769d5
View commit details
Copy full SHA for 38769d5
View code at this point
Browse repository at this point
fix(framework): HF-faithful TokenizerHub; shared GGUF metadata and ASR sampling; live assert tests
Show description for c562b7a
NairoDorian
and
claude
committed
c562b7a
View commit details
Copy full SHA for c562b7a
View code at this point
Browse repository at this point
moss codec: the Nano decoder attended over twice its intended window (fixes #663) (#664)
Show description for 68b8068
christopherthompson81
authored
68b8068
View commit details
Copy full SHA for 68b8068
View code at this point
Browse repository at this point
Clarify VAD audio chunking errors
0xShug0
committed
487800f
View commit details
Copy full SHA for 487800f
View code at this point
Browse repository at this point
Commits on Sep 22, 2026
gguf: quantize a tensor's rows in parallel (#649)
Show description for f6e2495
christopherthompson81
and
claude
authored
f6e2495
View commit details
Copy full SHA for f6e2495
View code at this point
Browse repository at this point
feat(audio8_tts): Falcon-H1 0.1B (Mamba2 + attention) support and codec/AR performance (#444)
Show description for 712dd75
gqf2008
authored
712dd75
View commit details
Copy full SHA for 712dd75
View code at this point
Browse repository at this point
Commits on Sep 21, 2026
Add shared mel and reference audio frontends (#629)
0xShug0
authored
779714d
View commit details
Copy full SHA for 779714d
View code at this point
Browse repository at this point
moss_tts_v15: MOSS-TTS-v1.5, and promote the moss_tts_delay family runtimes (#631)
Show description for 62e44c5
christopherthompson81
authored
62e44c5
View commit details
Copy full SHA for 62e44c5
View code at this point
Browse repository at this point
Commits on Sep 20, 2026
Share a configurable NeMo mel frontend across ASR models (#628)
Show description for e3de8e3
0xShug0
authored
e3de8e3
View commit details
Copy full SHA for e3de8e3
View code at this point
Browse repository at this point
Rebuild an ASR encoder graph when the cached one is too big (#619)
Show description for 9c00066
christopherthompson81
authored
9c00066
View commit details
Copy full SHA for 9c00066
View code at this point
Browse repository at this point
Commits on Sep 19, 2026
feat(model): add Confucius4-R2T2 real-time streaming ASR (r2t2_asr) (#604)
Show description for a7b58a6
davidxifeng
authored
a7b58a6
View commit details
Copy full SHA for a7b58a6
View code at this point
Browse repository at this point
zipvoice: add k2-fsa ZipVoice community TTS with zh/en frontend (#599)
Show description for 4b9a39f
davidxifeng
authored
4b9a39f
View commit details
Copy full SHA for 4b9a39f
View code at this point
Browse repository at this point
Commits on Sep 18, 2026
Add reusable Wan S2V framework components (#601)
0xShug0
authored
5185508
View commit details
Copy full SHA for 5185508
View code at this point
Browse repository at this point
Commits on Sep 17, 2026
fix(clap): materialize contiguous layout before the mel-projection matmul (#593)
Show description for 994c0cf
3 people
authored
994c0cf
View commit details
Copy full SHA for 994c0cf
View code at this point
Browse repository at this point
merge: reconcile upstream audio.cpp@main (c0b26a50, 53 commits)
Show description for 0686aab
NairoDorian
committed
0686aab
View commit details
Copy full SHA for 0686aab
View code at this point
Browse repository at this point
kokoro_tts: accept a supplied phoneme stream, bypassing the built-in G2P (#577)
Show description for df0e09e
christopherthompson81
and
claude
authored
df0e09e
View commit details
Copy full SHA for df0e09e
View code at this point
Browse repository at this point
Commits on Sep 16, 2026
Add Apollo, UniverSR and PulseVAD models (#583)
0xShug0
authored
23da5a1
View commit details
Copy full SHA for 23da5a1
View code at this point
Browse repository at this point
gguf: carry a GGUF input's embedded sidecars, and check the finished package against the one it was made from (#579)
Show description for 6b59e6e
christopherthompson81
and
claude
authored
6b59e6e
View commit details
Copy full SHA for 6b59e6e
View code at this point
Browse repository at this point
capi: list-valued request options (#566)
Show description for 39f9013
christopherthompson81
authored
39f9013
View commit details
Copy full SHA for 39f9013
View code at this point
Browse repository at this point
Reuse merged YuE2 LoRA weights across requests
0xShug0
committed
b09ba02
View commit details
Copy full SHA for b09ba02
View code at this point
Browse repository at this point
Add YuE2 AR LoRA support
0xShug0
committed
0d67b8d
View commit details
Copy full SHA for 0d67b8d
View code at this point
Browse repository at this point
Add framework support for load-time LoRA weight overlays
0xShug0
committed
bd80576
View commit details
Copy full SHA for bd80576
View code at this point
Browse repository at this point
qwen decode runtime: zero the KV cache in prefill_tokens_into_decode_cache() (#560)
Show description for 8c46ab9
engival
authored
8c46ab9
View commit details
Copy full SHA for 8c46ab9
View code at this point
Browse repository at this point
Commits on Sep 15, 2026
yue2: eager NAR attention on Intel Vulkan via yue2.attention session option (#557)
Show description for 6d4703e
engival
authored
6d4703e
View commit details
Copy full SHA for 6d4703e
View code at this point
Browse repository at this point
refactor(framework): promote greedy Qwen decoder runtime and Qwen BPE bundle helpers (#555)
Show description for 5f1b82b
gqf2008
authored
5f1b82b
View commit details
Copy full SHA for 5f1b82b
View code at this point
Browse repository at this point
streaming: publish partial text as increments, through one shared publisher (#552)
Show description for 3b90d6e
christopherthompson81
authored
3b90d6e
View commit details
Copy full SHA for 3b90d6e
View code at this point
Browse repository at this point
Fix Vulkan batched RoPE position alignment
0xShug0
committed
4611f3d
View commit details
Copy full SHA for 4611f3d
View code at this point
Browse repository at this point
Optimize Yue2 AR decode cache path
0xShug0
committed
b6509e3
View commit details
Copy full SHA for b6509e3
View code at this point
Browse repository at this point
Add SheetSage2 native runtime
0xShug0
committed
6cb5269
View commit details
Copy full SHA for 6cb5269
View code at this point
Browse repository at this point
Speed up Yue2 AR CFG decode
0xShug0
committed
e12cdff
View commit details
Copy full SHA for e12cdff
View code at this point
Browse repository at this point
Add Yue2 native model runtime and GGUF conversion
0xShug0
committed
c264137
View commit details
Copy full SHA for c264137
View code at this point
Browse repository at this point
Add opt-in encoder-decoder framework modules (#551)
0xShug0
authored
024297b
View commit details
Copy full SHA for 024297b
View code at this point
Browse repository at this point
Commits on Sep 14, 2026
refactor(asr): add WhisperBinTensorSource for .bin weight loading (B31 Part 1)
Show description for f6a9d2b
NairoDorian
and
CommandCodeBot
committed
f6a9d2b
View commit details
Copy full SHA for f6a9d2b
View code at this point
Browse repository at this point
Previous
Next
You can’t perform that action at this time.