Skip to content

Trainer of Speech Tokenizer(https://arxiv.org/abs/2308.16692)

active 2023-08-162026-03-25 (UTC)

Complete coverage26,707 / 26,707 hourly files (100%) · 2 absent upstream2023-08-152026-08-31 (UTC)
Events
422
Pushes
2
Pull requests
2
Issues
14
Stars
339
Forks
40

Activity over time

Daily event counts in the loaded window

Line chart, 953 days from 2023-08-16 to 2026-03-25. Pushes: 2 total, peak 1 in a day. Pull requests: 2 total, peak 1 in a day. Issues: 14 total, peak 1 in a day. Comments: 20 total, peak 9 in a day. Stars: 339 total, peak 6 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#54lth4563212025-04-09 02:15
    problem of loss
  • Issue comment#40zhangshengoo2025-03-19 02:45
    Encodec's training speed
  • Issue#53JohnHerry2025-03-07 01:14
    How to use Hifi-Codec as speech encoder in LLM based TTS?
  • Issue comment#53yongaifadian12025-03-06 17:13
    How to use Hifi-Codec as speech encoder in LLM based TTS?
  • Issue comment#52wj-gxy2025-02-25 03:01
    RuntimeError: Default process group has not been initialized, please make sure to call init_process_group.
  • Issue#53JohnHerry2024-08-22 10:24
    How to use Hifi-Codec as speech encoder in LLM based TTS?
  • Issue#52zjj13332024-07-19 07:31
    RuntimeError: Default process group has not been initialized, please make sure to call init_process_group.
  • Issue comment#40zhaojingxin1232024-07-02 08:25
    Encodec's training speed
  • Issue comment#50yangdongchao2024-06-27 03:50
    why norm wav when inference?
  • Issue comment#51yangdongchao2024-06-27 03:50
    About the experimental settings in the paper "HIFI-CODEC: GROUP-RESIDUAL VECTOR QUANTIZATION FOR HIGH FIDELITY AUDIO CODEC"
  • Issue#51Shengqiang-Li2024-05-14 10:59
    About the experimental settings in the paper "HIFI-CODEC: GROUP-RESIDUAL VECTOR QUANTIZATION FOR HIGH FIDELITY AUDIO CODEC"
  • Issue#50fengshi-cherish2024-04-06 09:11
    why norm wav when inference?
  • Issue#49JohnHerry2024-03-29 08:25
    What is the RTF of HiFiCodec decoder?
  • Issue#48Mahaotian12024-02-29 01:25
    it does not converge for valle training
  • Pull request#47yangdongchao2023-12-27 08:22
  • Issue#5listener172023-11-21 05:34
    Command line to train EnCodec
  • Issue#46TechInterMezzo2023-11-01 09:54
    License missing
  • Issue#17Firefang0032023-09-04 11:35
    Hi,Do you have any plans to open source the pre-trained model of soundstream?
  • Issue comment#17UkiTenzai2023-08-31 02:52
    Hi,Do you have any plans to open source the pre-trained model of soundstream?
  • Issue#45UkiTenzai2023-08-31 01:22
    请问有训练好的模型吗
  • Issue#44UkiTenzai2023-08-29 08:56
    自定义库distributed.py的import问题
  • Issue comment#43NoFish-5282023-08-29 04:46
    将多卡/单卡的权重保存成同一种格式;支持shell脚本中data为多个字符串的输入;修改test文件
  • Issue comment#43yt6051556242023-08-29 04:45
    将多卡/单卡的权重保存成同一种格式;支持shell脚本中data为多个字符串的输入;修改test文件
  • Issue comment#43NoFish-5282023-08-29 04:30
    将多卡/单卡的权重保存成同一种格式;支持shell脚本中data为多个字符串的输入;修改test文件
  • Issue comment#43yt6051556242023-08-29 04:06
    将多卡/单卡的权重保存成同一种格式;支持shell脚本中data为多个字符串的输入;修改test文件

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 339 stars here means stars gained during the window, not the repo's star count.