Skip to content

Pull requests: espnet/espnet

New pull request New
53 Open 3,586 Closed
53 Open 3,586 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

[SpeechLM] Add Qwen3-Omni Audio Encoder Enhancement Enhancement ESPnet2 size:L This PR changes 100-499 lines, ignoring generated files.
#6311 opened Nov 25, 2025 by Qingzheng-Wang Loading…
3
Add epsilon to standard deviation for normalization Bugfix ESPnet2 SE Speech enhancement size:XS This PR changes 0-9 lines, ignoring generated files.
#6309 opened Nov 24, 2025 by LiChenda Loading… v.202512
3
[SpeechLM] Add Xcodec Support ESPnet2 New Features size:M This PR changes 30-99 lines, ignoring generated files.
#6308 opened Nov 24, 2025 by Qingzheng-Wang Loading…
8
[SVS]: fix: fix visinger2 inference Bugfix ESPnet2 size:S This PR changes 10-29 lines, ignoring generated files.
#6306 opened Nov 21, 2025 by South-Twilight Loading… v.202512
4
[espnet3-10] Merge espnet3 branch into master ASR Automatic speech recogntion CI Travis, Circle CI, etc Documentation ESPnet1 ESPnet2 ESPnet3 Installation LM mergify MT Machine translation size:XXL This PR changes 1000+ lines, ignoring generated files. TTS Text-to-speech
#6304 opened Nov 17, 2025 by Masao-Someki Loading…
38
fix CategoryChunkIterFactory Bugfix ESPnet2 lgtm This PR has been approved by a maintainer size:M This PR changes 30-99 lines, ignoring generated files.
#6302 opened Nov 16, 2025 by whr-a Loading… v.202512
8
Add BSCodec implementation and recipe Codec ESPnet2 README Recipe size:XXL This PR changes 1000+ lines, ignoring generated files.
#6297 opened Nov 13, 2025 by whr-a Loading… v.202512
8
Add Emilia TTS recipe (ESPnet Bootcamp) ESPnet2 README Recipe size:XL This PR changes 500-999 lines, ignoring generated files. TTS Text-to-speech
#6291 opened Nov 6, 2025 by NewGamezzz Loading… v.202512
13
Add arkive data loading ESPnet2 New Features size:L This PR changes 100-499 lines, ignoring generated files.
#6287 opened Nov 4, 2025 by wanchichen Loading… v.202512
26
Add Marathi LREC2020 ASR recipe (ESPnet bootcamp) ASR Automatic speech recogntion ESPnet2 README Recipe size:XL This PR changes 500-999 lines, ignoring generated files.
#6274 opened Oct 25, 2025 by Aniket-Tathe Loading… v.202512
13
[espnet3-9] Add Librispeech-100h ASR recipe ASR Automatic speech recogntion conflicts Documentation ESPnet3 Installation Recipe size:XL This PR changes 500-999 lines, ignoring generated files.
#6271 opened Oct 24, 2025 by Masao-Someki Loading… v.202512
77
[WIP]Turn by turn CoT SDS conflicts ESPnet1 ESPnet2 Installation README size:XXL This PR changes 1000+ lines, ignoring generated files. SLU Spoken language understanding
#6269 opened Oct 23, 2025 by siddhu001 Loading… v.202512
30
Update torch AMP autocast syntax for CUDA compatibility Enhancement Enhancement ESPnet2 size:XS This PR changes 0-9 lines, ignoring generated files.
#6267 opened Oct 20, 2025 by KanTakahiro Loading… v.202512
3
egs2/libritts_r/tts1: add recipe skeleton (conf/, run.sh, path.sh) an… ESPnet2 README Recipe size:M This PR changes 30-99 lines, ignoring generated files. TTS Text-to-speech
#6256 opened Oct 2, 2025 by ZhuoyanTao Loading… v.202512
6
Create recipe for myst_ogi_cmu_kids ASR Automatic speech recogntion ESPnet2 README Recipe size:XXL This PR changes 1000+ lines, ignoring generated files.
#6222 opened Aug 23, 2025 by anyuyay Loading… v.202512
13
LID-9: Geolocation-aware LID recipe and codes ESPnet2 New Features README size:XXL This PR changes 1000+ lines, ignoring generated files.
#6212 opened Aug 20, 2025 by Qingzheng-Wang Loading… v.202512
29
egs2/globe: add multi‑speaker English TTS recipe (GLOBE‑v2) ESPnet2 README Recipe size:XXL This PR changes 1000+ lines, ignoring generated files. TTS Text-to-speech
#6185 opened Jul 14, 2025 by ZhuoyanTao Loading… v.202512
38
Update attention.py, using SDPA by default Enhancement Enhancement ESPnet1 size:S This PR changes 10-29 lines, ignoring generated files.
#6149 opened Jun 13, 2025 by popcornell Loading… v.202512
13
Adding vanilla EEND recipe for AMI with multi speaker synthetic data simulation included. CI Travis, Circle CI, etc conflicts Docker Documentation ESPnet1 ESPnet2 Installation README
#6138 opened Jun 11, 2025 by popcornell • Draft v.202512
2
Fixed a typo that was causing data leakage. ESPnet2 OWSM Open Whisper-style Speech Model size:XS This PR changes 0-9 lines, ignoring generated files.
#6131 opened Jun 6, 2025 by Abdigal1 Loading… v.202512
14
TTS recipe for Expresso Dataset CI Travis, Circle CI, etc ESPnet2 Installation README size:XXL This PR changes 1000+ lines, ignoring generated files.
#6125 opened May 30, 2025 by lism13 Loading… v.202512
4
Add demo for a tool use enabled Reasoning Agent ESPnet2 New Features README size:XXL This PR changes 1000+ lines, ignoring generated files.
#6100 opened Apr 26, 2025 by leandermaben Loading… v.202512
13
Ser for msp podcast CI Travis, Circle CI, etc ESPnet2 New Features README Recipe size:XXL This PR changes 1000+ lines, ignoring generated files.
#6096 opened Apr 21, 2025 by Subohao Loading… v.202512
64
Codec Major Updates Codec ESPnet2 New Features README size:XXL This PR changes 1000+ lines, ignoring generated files.
#6093 opened Apr 15, 2025 by ftshijt Loading… v.202512
27
Add Harvest algorithm as an option for F0 extraction ESPnet2 Help wanted Need help New Features TTS Text-to-speech
#6083 opened Apr 1, 2025 by f-matano44 Loading… v.202512
7
ProTip! Filter pull requests by the default branch with base:master.