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 }}
NVIDIA-NeMo
Speech
Repository navigation
Code
Issues
136
(136)
Pull requests
199
(199)
Discussions
Actions
Projects
Security and quality
2
(2)
Insights
More
items
All pull requests
New pull request
Search pull requests
is
:
pr
state
:
open
is:pr state:open
Clear filter
Search
Pull requests
Open
199
(199)
Closed
12,230
(12,230)
Author
Label
Projects
Milestones
Reviews
Assignee
Sort by
Newest
descending
More items
Comfortable display density
Compact display density
ci(code-freeze): use github app authentication
CI
#16348
·
ko3n1g
opened
Oct 7, 2026
Contributor
·
2 of 3 tasks
·
·
1
[TTS] Comparison report: show the target recording in the audio report
TTS
#16346
·
XuesongYang
opened
Oct 7, 2026
Collaborator
·
2/2
·
5 of 8 tasks
·
·
4
[TTS] Comparison report: context-type gating and SSIM (pred vs GT) in statistical tests
TTS
#16345
·
XuesongYang
opened
Oct 7, 2026
Collaborator
·
1/2
·
8 tasks done
·
·
6
SALM vLLM: serve CTC word timestamps and speaker diarization
ASR
#16344
·
DongjiGao
opened
Oct 7, 2026
Contributor
·
·
1
fix(asr): fix ConvSubsampling forward for chunking=-1, conv1d, and vggnet (#16223)
ASR
community-request
#16342
·
Kuldeeep18
opened
Oct 6, 2026
·
6 of 8 tasks
·
·
1
1
SpeechLM vLLM: serve FP8-quantized checkpoints (FP8 decoder + prequantized FP8 audio encoder)
ASR
#16341
·
DongjiGao
opened
Oct 5, 2026
Contributor
·
6 of 8 tasks
·
·
13
feat(diarization): add soft_label_thres for binarized label configura…
community-request
Speaker Tasks
#16340
·
m15kh
opened
Oct 5, 2026
·
3 of 5 tasks
·
·
1
fix(asr): use window_stride when shifting frame offsets of merged hour-long chunks
ASR
community-request
waiting-on-maintainers
#16339
·
ShivamSharma43
opened
Oct 4, 2026
·
1 task done
·
·
1
2
fix(configs): point SALM and beamforming _target_ entries at existing classes
audio
community-request
waiting-on-maintainers
#16338
·
ShivamSharma43
opened
Oct 4, 2026
·
1 task done
·
·
1
2
Remove unused bin_loss_scale from AlignerModel
community-request
TTS
waiting-on-maintainers
#16337
·
ShivamSharma43
opened
Oct 4, 2026
·
2 of 7 tasks
·
·
1
2
fix(tokenizers): support pangu>=5.0.0 and space_text API (#16317)
common
community-request
waiting-on-maintainers
#16335
·
DYNOSuprovo
opened
Oct 3, 2026
·
6 of 8 tasks
·
·
1
1
fix(tts): PositionalEmbedding.inv_freq silently loses precision under bf16-true
community-request
TTS
waiting-on-maintainers
#16334
·
tritsystem
opened
Oct 3, 2026
·
4 tasks done
·
·
1
fix(asr): resample multichannel audio along the time axis
ASR
community-request
waiting-on-maintainers
#16333
·
dheeraj-juvvadi
opened
Oct 3, 2026
·
4 tasks done
·
·
2
2608 tts training
common
TTS
#16332
·
paarthneekhara
opened
Oct 1, 2026
Collaborator
·
·
1
fix(asr): wait for the device-to-host copy in greedy CTC decoding
ASR
community-request
waiting-on-maintainers
#16331
·
1fanwang
opened
Oct 1, 2026
·
3 of 8 tasks
·
·
1
fix(asr): keep CUDA graph decoder memory across empty_cache()
ASR
community-request
core
waiting-on-maintainers
#16330
·
1fanwang
opened
Oct 1, 2026
·
3 of 8 tasks
·
·
1
1
fix(asr): fall back to "text" in cal_write_wer when gt_text_attr_name is missing
ASR
community-request
waiting-on-maintainers
#16327
·
MohammadHijjawi97
opened
Sep 30, 2026
·
3 of 8 tasks
·
·
1
fix(common): collect whole labels in FeatureLabel.uniq_labels
ASR
common
community-request
waiting-on-maintainers
#16326
·
MohammadHijjawi97
opened
Sep 30, 2026
·
3 of 8 tasks
·
·
1
1
Speak one dollar and one cent in the singular
common
community-request
waiting-on-maintainers
#16324
·
SashaMIT
opened
Sep 30, 2026
·
4 of 5 tasks
·
·
1
fix(asr): omit empty words from timestamp offsets
ASR
community-request
waiting-on-maintainers
#16323
·
patelnav
opened
Sep 30, 2026
·
·
1
fix(asr): drop a buffered stream's bufferer when its state is deleted
ASR
community-request
waiting-on-maintainers
#16322
·
kzos
opened
Sep 30, 2026
Contributor
·
3 of 7 tasks
·
·
1
fix(asr): free cache-aware slots on delete_state and session reset
ASR
community-request
waiting-on-maintainers
#16321
·
dundysm
opened
Sep 30, 2026
·
4 of 7 tasks
·
·
1
9
Remove the memory handlers from the logger once the files are added
community-request
waiting-on-maintainers
#16320
·
v0ropaev
opened
Sep 30, 2026
·
·
1
Support gzip JSONL in indexed dataloading and pack workflows
common
#16319
·
pzelasko
opened
Sep 30, 2026
Collaborator
·
7 tasks done
·
·
1
Fully disable alignment prior creation for EMTTS
TTS
#16316
·
rfejgin
opened
Sep 28, 2026
Collaborator
·
·
5
Previous
1
2
3
4
5
6
7
8
Next
You can’t perform that action at this time.