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
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
fix(voxtral_realtime): cached graphs decoded garbage on reuse; offline delay 30
Show description for a22a2da
NairoDorian
and
claude
committed
a22a2da
View commit details
Copy full SHA for a22a2da
View code at this point
Browse repository at this point
fix(runtime): adopt transcribe.cpp S3 conformer memory, parakeet tail loss, scratch release
Show description for 482c9a7
NairoDorian
and
claude
committed
482c9a7
View commit details
Copy full SHA for 482c9a7
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
feat(capi): Whisper C-ABI takeover by the engine; retire the Whisper arch (Phase 11 W2b.2, B16c)
Show description for beb2453
NairoDorian
and
claude
committed
beb2453
View commit details
Copy full SHA for beb2453
View code at this point
Browse repository at this point
feat(whisper): engine Whisper with the full decoding recipe and GGUF loading (Phase 11 W2b.1)
Show description for 921631b
NairoDorian
and
claude
committed
921631b
View commit details
Copy full SHA for 921631b
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
fix(runtime): adopt transcribe.cpp #165 decode budget; triage ledger to 0a67b65b
Show description for 1f2802f
NairoDorian
and
claude
committed
1f2802f
View commit details
Copy full SHA for 1f2802f
View code at this point
Browse repository at this point
Update Nemotron 3 diarization to the released BF16 checkpoint
0xShug0
committed
57186a8
View commit details
Copy full SHA for 57186a8
View code at this point
Browse repository at this point
Reduce Nemotron-3 diarization graph memory usage
0xShug0
committed
f5a5552
View commit details
Copy full SHA for f5a5552
View code at this point
Browse repository at this point
Add Nemotron-3-Diarization (preview) support
Show description for 4b11168
0xShug0
authored
4b11168
View commit details
Copy full SHA for 4b11168
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
Add Moonshine ASR audio chunking (#662)
Faazil-jpg
authored
ab26890
View commit details
Copy full SHA for ab26890
View code at this point
Browse repository at this point
Scope native batching to transcription endpoint
0xShug0
committed
f165a21
View commit details
Copy full SHA for f165a21
View code at this point
Browse repository at this point
Add Nemotron 3 diarization support
0xShug0
committed
dfb4468
View commit details
Copy full SHA for dfb4468
View code at this point
Browse repository at this point
Merge pull request #658 from pnnbao97/pr/vieneu-followup
Show description for a6049da
pnnbao97
authored
a6049da
View commit details
Copy full SHA for a6049da
View code at this point
Browse repository at this point
Add LiveAvatar to WebUI
0xShug0
committed
1ff4c95
View commit details
Copy full SHA for 1ff4c95
View code at this point
Browse repository at this point
Allow empty lyrics for YuE2 instrumental generation
0xShug0
committed
0f9306e
View commit details
Copy full SHA for 0f9306e
View code at this point
Browse repository at this point
Commits on Sep 22, 2026
Fix Seed-VC V1 F0 conditioning (#653)
0xShug0
authored
4e8be77
View commit details
Copy full SHA for 4e8be77
View code at this point
Browse repository at this point
moss_tts_v15: declare the text chunking options in the spec (#654)
Show description for 1ee4ce8
christopherthompson81
authored
1ee4ce8
View commit details
Copy full SHA for 1ee4ce8
View code at this point
Browse repository at this point
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
yue2: continue a song from given semantic tokens (#641)
Show description for d32a6a0
engival
authored
d32a6a0
View commit details
Copy full SHA for d32a6a0
View code at this point
Browse repository at this point
vieneu_v3_turbo (formerly vietneu_tts): reference-code conditioning, Python sampling parity, official GGUF — from the model author (#647)
Show description for 8d5e10a
3 people
authored
8d5e10a
View commit details
Copy full SHA for 8d5e10a
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
yue2: tile the eager NAR attention so long songs fit a 4 GiB buffer (#642)
Show description for 5d786f9
engival
authored
5d786f9
View commit details
Copy full SHA for 5d786f9
View code at this point
Browse repository at this point
yue2: stop_after ends a run after the score or the semantic stage (#636)
Show description for 2fff3c8
engival
authored
2fff3c8
View commit details
Copy full SHA for 2fff3c8
View code at this point
Browse repository at this point
perf(roformer): pipeline CUDA chunk processing (#633)
Show description for 741fe03
mirek190
authored
741fe03
View commit details
Copy full SHA for 741fe03
View code at this point
Browse repository at this point
Commits on Sep 21, 2026
yue2: export the semantic token stream as a result artifact (#635)
Show description for f0e3a90
engival
authored
f0e3a90
View commit details
Copy full SHA for f0e3a90
View code at this point
Browse repository at this point
kokoro_tts: report the durations it already predicts as word timings (#626)
Show description for 2792c65
christopherthompson81
and
claude
authored
2792c65
View commit details
Copy full SHA for 2792c65
View code at this point
Browse repository at this point
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
Improve Nemotron ASR streaming (#630)
0xShug0
authored
9aa53fe
View commit details
Copy full SHA for 9aa53fe
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
Previous
Next
You can’t perform that action at this time.