PHANTOM
🇮🇳 IN
Skip to content

Pull requests: espnet/espnet

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
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort

Pull requests list

Bump rollup from 4.22.4 to 4.59.0 in /doc/vuepress dependencies Pull requests that update a dependency file Documentation javascript Pull requests that update javascript code size:XS This PR changes 0-9 lines, ignoring generated files.
#6378 opened Feb 26, 2026 by dependabot bot Loading…
fix: replace 24 bare except clauses with except Exception Bugfix ESPnet2 size:XXL This PR changes 1000+ lines, ignoring generated files.
#6377 opened Feb 25, 2026 by haosenwang1018 Loading…
FastSpeech2: Add shape-bucketing for XPU inference and torch.compile … ESPnet2 size:L This PR changes 100-499 lines, ignoring generated files. TTS Text-to-speech
#6376 opened Feb 25, 2026 by jthakurH Loading…
[Test for Claude Code, Draft] Add speaker identification system to espnet3 ESPnet3 New Features SID Speaker identification/embedding size:XL This PR changes 500-999 lines, ignoring generated files.
#6375 opened Feb 24, 2026 by sw005320 Loading…
2 tasks
Added CommonVoice gender-based ASR fairness recipe ASR Automatic speech recogntion ESPnet2 README Recipe size:XL This PR changes 500-999 lines, ignoring generated files.
#6368 opened Feb 19, 2026 by Srishtiginjala Loading… v.202601
fix: raise NotImplementedError and avoid mutable default args Bugfix ESPnet2 size:S This PR changes 10-29 lines, ignoring generated files.
#6363 opened Feb 11, 2026 by Mr-Neutr0n Loading…
1 of 3 tasks
v.202601
Fix division by zero in CTC builtin2 when all samples have NaN grad ASR Automatic speech recogntion Bugfix ESPnet2 size:XS This PR changes 0-9 lines, ignoring generated files.
#6362 opened Feb 11, 2026 by Mr-Neutr0n Loading…
2 tasks
v.202601
[WIP] Add TSE task/system code and LibriMix recipe for ESPnet3 ESPnet2 ESPnet3 Recipe SE Speech enhancement size:XXL This PR changes 1000+ lines, ignoring generated files.
#6357 opened Feb 6, 2026 by Emrys365 Loading… v.202601
[SpeechLM] Multimodal IO ESPnet2 New Features size:L This PR changes 100-499 lines, ignoring generated files.
#6355 opened Feb 2, 2026 by jctian98 Loading… v.202601
[SpeechLM] Trainer, processor and model ESPnet2 lgtm This PR has been approved by a maintainer LM size:XXL This PR changes 1000+ lines, ignoring generated files.
#6354 opened Feb 2, 2026 by jctian98 Loading… v.202601
[SpeechLM] Update data loading files ESPnet2 size:XXL This PR changes 1000+ lines, ignoring generated files.
#6353 opened Feb 2, 2026 by jctian98 Loading… v.202601
[espnet3-14.5] Bug fix for data organizer and dataloader Bugfix CI Travis, Circle CI, etc conflicts ESPnet3 Installation size:XXL This PR changes 1000+ lines, ignoring generated files.
#6350 opened Jan 30, 2026 by Masao-Someki Loading… v.202601
[pre-commit.ci] pre-commit autoupdate dependencies Pull requests that update a dependency file ESPnet2 size:L This PR changes 100-499 lines, ignoring generated files.
#6344 opened Jan 19, 2026 by pre-commit-ci bot Loading… v.202601
[espnet3-16] Add demo stage CI Travis, Circle CI, etc ESPnet2 ESPnet3 Installation New Features size:XXL This PR changes 1000+ lines, ignoring generated files.
#6342 opened Jan 19, 2026 by Masao-Someki Loading…
inference trick from: "Improving Cross-Attention based on Positional Alignment during Inference for Robust Long-form Speech Recognition" ASR Automatic speech recogntion ESPnet2 size:L This PR changes 100-499 lines, ignoring generated files.
#6339 opened Jan 16, 2026 by Miamoto Loading…
[espnet3-15] Add publication stage CI Travis, Circle CI, etc conflicts ESPnet2 ESPnet3 New Features size:XXL This PR changes 1000+ lines, ignoring generated files.
#6338 opened Jan 16, 2026 by Masao-Someki Loading…
[espnet3-14] Add integration test CI Travis, Circle CI, etc ESPnet2 ESPnet3 Installation size:XXL This PR changes 1000+ lines, ignoring generated files.
#6331 opened Dec 26, 2025 by Masao-Someki Loading… v.202601
[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… v.202601
[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… v.202601
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.202601
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.202601
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.202601
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.202601
ProTip! Filter pull requests by the default branch with base:master.