Skip to content

Foundational Model for Speech Recognition Tasks

Python · active 2025-03-022026-07-14 (UTC)

Partial coverage11,566 / 12,653 hourly files (91%) · 2 absent upstream · 1,083 failed, retryable2025-03-012026-08-10 (UTC)— sampled evenly across the window, so rankings and trends hold; absolute counts scale up.
Events
226
Pushes
6
Pull requests
10
Issues
14
Stars
142
Forks
23

Activity over time

Daily event counts in the loaded window

Line chart, 500 days from 2025-03-02 to 2026-07-14. Pushes: 6 total, peak 2 in a day. Pull requests: 10 total, peak 2 in a day. Issues: 14 total, peak 5 in a day. Comments: 23 total, peak 5 in a day. Stars: 142 total, peak 7 in a day.

  • Pushes
  • Pull requests
  • Issues
  • Comments
  • Stars

Stars, PRs, issues and forks are under-captured in the later part of this window. GH Archive progressively stopped capturing non-push events during 2026 — −95% or worse by the end of the window. Every series here except Pushes fades for that reason, so a decline above reflects the archive, not this repository. Pushes stay reliable throughout, so read them, and the contributor counts derived from them, as the real signal. Data health has the measurements.

Top contributors

Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity

Recent activity

Latest issues, pull requests and releases

  • Issue comment#68uadiasas2026-05-04 09:44
    Утечка оперативной памяти при использовании giga am v3 e2e rnnt на gpu
  • Issue comment#61misteral2026-03-15 12:22
    feat: GigaAM v3 CTC inference on Apple Silicon via MLX
  • Pull request#61misteral2026-03-15 12:13
  • Issue comment#55slavonnet2026-03-11 09:45
    Transcribing multi-channel audio (Channel deorization)
  • Pull request#58Alexander41272026-02-12 19:33
  • Issue#57Reuelster2026-01-30 07:58
    Model.from_pretrained() fails with local path in vad_utils.py (commit 8e78880)
  • Issue comment#55slavonnet2026-01-14 01:31
    Transcribing multi-channel audio (Channel deorization)
  • Issue comment#18slavonnet2026-01-13 02:22
    streaming inference and diarization
  • Issue comment#50Alexander41272025-12-26 11:43
    Suggestion: Allow local loading of "pyannote/segmentation-3.0" model to avoid repeated HuggingFace downloads
  • Pull request#54Alexander41272025-12-26 11:43
  • Pull request#54Alexander41272025-12-26 11:08
  • Issue comment#18ivkond2025-12-06 00:24
    streaming inference and diarization
  • Pull request#53Alexander41272025-12-05 11:36
  • Issue comment#48mirix2025-11-26 15:29
    Word-level timestamps
  • Issue comment#48Maksim-Goncharovskiy2025-11-25 11:07
    Word-level timestamps
  • Issue comment#49istupakov2025-11-24 13:48
    Difference in preprocessor results
  • Issue#50G7A4T52025-11-23 22:07
    Suggestion: Allow local loading of "pyannote/segmentation-3.0" model to avoid repeated HuggingFace downloads
  • Issue#49istupakov2025-11-23 18:22
    Difference in preprocessor results
  • Issue comment#47mmarsreg2025-11-21 07:42
    GigaAM-v3
  • Issue comment#22georgygospodinov2025-11-20 19:30
    Added support to transcribe numpy.ndarray objects
  • Issue comment#41georgygospodinov2025-11-20 19:01
    ERROR during transcription: The size of tensor a (5082) must match the size of tensor b (5000) at non-singleton dimension 0
  • Pull request#47Alexander41272025-11-20 10:30
  • Issue comment#18mmarsreg2025-11-20 08:10
    streaming inference and diarization
  • Issue#3georgygospodinov2025-11-08 11:48
    strangely, many empty transcriptions on mozilla common voice
  • Issue comment#3georgygospodinov2025-11-08 11:48
    strangely, many empty transcriptions on mozilla common voice

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 142 stars here means stars gained during the window, not the repo's star count.