Issues

• Update install dependencies

  ZhangXInFD/SpeechTokenizer#30 · Filter by author mattpitkin opened on Nov 3, 2025

• Unable to Reproduce Checkpoint Results (Especially Distillation)

  ZhangXInFD/SpeechTokenizer#28 · Filter by author ggiggit opened on Mar 10, 2025
  4

• broadcast_tensor in core_vq.py for multi_gpu training

  ZhangXInFD/SpeechTokenizer#24 · Filter by author mindmapper15 opened on Nov 12, 2024

• Discriminator weights

  ZhangXInFD/SpeechTokenizer#23 · Filter by author LaurinmyReha opened on Oct 31, 2024

• Question about size when training

  ZhangXInFD/SpeechTokenizer#22 · Filter by author LiuMY13 opened on Oct 29, 2024
  3

• 请问一下semantic distillation在哪个py文件中有体现呀，没找到呢

  ZhangXInFD/SpeechTokenizer#21 · Filter by author AlphaMind123 opened on Oct 23, 2024

• 用readme里面的示例代码进行语音的重构，发现重构wav的采样点数量和原始wav的采样点数量不一样

  ZhangXInFD/SpeechTokenizer#20 · Filter by author AlphaMind123 opened on Oct 23, 2024

• 请问用这个模型能提取出表征音频的连续向量吗？

  ZhangXInFD/SpeechTokenizer#19 · Filter by author AlphaMind123 opened on Oct 23, 2024

• a bug in EuclideanCodebook

  ZhangXInFD/SpeechTokenizer#18 · Filter by author krgy12138 opened on Oct 5, 2024

• bitrate of pretrained models

  ZhangXInFD/SpeechTokenizer#17 · Filter by author gen35 opened on Sep 12, 2024
  1

• Can we generate audio from just semantic tokens?

  ZhangXInFD/SpeechTokenizer#16 · Filter by author macabdul9 opened on Aug 29, 2024
  1

• Ask for number range of training loss.

  ZhangXInFD/SpeechTokenizer#15 · Filter by author liangpenglong opened on Aug 27, 2024

• changing hubert model to another model

  ZhangXInFD/SpeechTokenizer#14 · Filter by author acul3 opened on Jul 28, 2024

• 10 batchsize = 63.72G???(All File are 3s wav)

  ZhangXInFD/SpeechTokenizer#13 · Filter by author coding-sharks opened on Jul 16, 2024
  1

• ImportError: cannot import name 'split_torch_state_dict_into_shards' from 'huggingface_hub'

  ZhangXInFD/SpeechTokenizer#12 · Filter by author ehosseiniasl opened on Jul 6, 2024
  2

• Cross-lingual

  ZhangXInFD/SpeechTokenizer#11 · Filter by author coding-sharks opened on Jun 29, 2024
  1

• zero grad issus in encodec?

  ZhangXInFD/SpeechTokenizer#10 · Filter by author yuzuda283 opened on Jun 11, 2024
  4

• How to deal with the integer values of RVQ

  ZhangXInFD/SpeechTokenizer#5 · Filter by author phdshliang opened on Apr 1, 2024
  2