Skip to content

Official Implementation of StyleTTS

active 2023-08-152026-04-12 (UTC)

Complete coverage26,791 / 26,791 hourly files (100%) · 2 absent upstream2023-08-152026-09-04 (UTC)
Events
410
Pushes
2
Pull requests
3
Issues
50
Stars
200
Forks
34

Activity over time

Daily event counts in the loaded window

Line chart, 972 days from 2023-08-15 to 2026-04-12. Pushes: 2 total, peak 1 in a day. Pull requests: 3 total, peak 1 in a day. Issues: 50 total, peak 3 in a day. Comments: 121 total, peak 9 in a day. Stars: 200 total, peak 5 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#82LoganLiu662025-11-27 12:19
    Random burst noises in the generated audio
  • Issue#82LoganLiu662025-11-27 12:19
    Random burst noises in the generated audio
  • Issue#82LoganLiu662025-11-26 08:41
    Random burst noises in the generated audio
  • Issue comment#74magicse2025-08-03 15:35
    MelSpectrogram() and unspecified sampling rate
  • Issue comment#81Respaired2025-01-23 20:51
    Unable to Access Pretrained Hifi-GAN and StyleTTS Model Links
  • Issue comment#76Oddadmix2025-01-23 04:05
    can't import mask_from_lens from monotonic_align
  • Issue comment#76cnint06272025-01-08 04:24
    can't import mask_from_lens from monotonic_align
  • Issue comment#76cmyHuawei2025-01-07 15:58
    can't import mask_from_lens from monotonic_align
  • Issue#80gnitoah2025-01-02 09:47
    Questions regarding the pretrained text aligner
  • Issue#79Atharva10062024-12-10 07:01
    Finetune multispeaker model
  • Issue#78Atharva10062024-11-19 04:45
    Train both stages consecutively
  • Issue comment#74gnitoah2024-09-07 19:54
    MelSpectrogram() and unspecified sampling rate
  • Issue comment#74gnitoah2024-09-07 19:54
    MelSpectrogram() and unspecified sampling rate
  • Issue#77cnint06272024-09-03 08:50
    Is there a first-stage pretrained model?
  • Issue comment#62niranjanakella2024-08-18 10:51
    Inference exact time for each word
  • Issue comment#62niranjanakella2024-08-17 04:34
    Inference exact time for each word
  • Issue#75CasonTsai2024-07-30 14:51
    amazing work,can it support that generate the phoneme delayed time sequence?
  • Issue comment#62alessandropettenuzzo962024-07-04 16:45
    Inference exact time for each word
  • Issue comment#10starmoon-11342024-06-14 04:17
    mandrain support?
  • Issue#74dsplog2024-05-05 01:49
    MelSpectrogram() and unspecified sampling rate
  • Issue comment#3vishalsantoshi2024-03-24 12:09
    Is it possible to control the speed of the speech?
  • Issue comment#10hyzhan2024-03-14 01:54
    mandrain support?
  • Issue#73Anshu-Kumar-12024-02-14 08:07
    Voice Quality Issues using Librispeech
  • Issue#72raushanagrawal2024-01-29 05:44
    Marathi Support ?
  • Issue comment#53SoshyHayami2024-01-25 09:50
    多卡训练的问题

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 200 stars here means stars gained during the window, not the repo's star count.