6 Pull requests merged by 6 people

• Add mirrors for torch

  #857 merged Jan 26, 2025

• feat(demo): Add Colab badge and ensure output directory is created

  #844 merged Jan 23, 2025

• docs: adjust the chapter structure to better organize the model downl…

  #839 merged Jan 23, 2025

• chore: typo fix on zh/start_agent.md

  #835 merged Jan 23, 2025

• Fix: correct typo

  #849 merged Jan 23, 2025

• support ipv6

  #850 merged Jan 23, 2025

2 Pull requests opened by 2 people

• Fixed: FutureWarning: `torch.backends.cuda.sdp_kernel()` is deprecated.

  #859 opened Jan 26, 2025

• Feat: Optimize text cleaning by expanding emoji removal support and refining regex for arrow, Arabic, and Hebrew symbol filtering.

  #861 opened Jan 27, 2025

13 Issues closed by 3 people

• /v1/asr endpoint seems not working in api

  #681 closed Jan 28, 2025

• What is this problem ？index out of range in self

  #750 closed Jan 28, 2025

• add '--workers' args for tools/api_server.py,i cannot run it

  #732 closed Jan 27, 2025

• I do finetuning but I just hear a uniform low beep not speech

  #845 closed Jan 26, 2025

• Streaming breaks with finetuned model

  #848 closed Jan 26, 2025

• sentence with "/" has a bug.

  #846 closed Jan 26, 2025

• Chinese pronunciation

  #847 closed Jan 26, 2025

• Why training is finished after some specific iterations?

  #851 closed Jan 26, 2025

• The pitch is unstable.

  #640 closed Jan 26, 2025

• Add a documentation page for data quality required for fine-tuning

  #598 closed Jan 25, 2025

• When deploying the agent to the final step, the Gradio page has already appeared, but an error is reported when starting a conversation.

  #715 closed Jan 25, 2025

• Generated audio or audio stream issues

  #724 closed Jan 24, 2025

• Please create a discussion group. The QR code of WeChat group given is no longer valid.

  #726 closed Jan 24, 2025

4 Issues opened by 3 people

• add persian language

  #863 opened Jan 28, 2025

• --compile crack

  #860 opened Jan 26, 2025

• LoRA Training Taking Longer Than Expected Compared to ViTs or Other Models

  #855 opened Jan 24, 2025

• Low Model Accuracy After Extended Training with Unicode-Based Language

  #852 opened Jan 24, 2025

17 Unresolved conversations

Sometimes conversations happen on old items that aren’t yet closed. Here is a list of all the Issues and Pull Requests with unresolved conversations.

• How to forcely control the output length (duration)?

  #816 commented on Jan 24, 2025 • 0 new comments

• [Feature]How can I specify that characters are silent and that pinyin or English words are read automatically?

  #497 commented on Jan 24, 2025 • 0 new comments

• [BUG]The audio generated by the streaming request is noisy. How can I solve this problem?

  #509 commented on Jan 24, 2025 • 0 new comments

• Why is the streaming parameter of the TTS interface set to True, which actually returns all fragments instead of streaming

  #819 commented on Jan 24, 2025 • 0 new comments

• New language adaptation

  #763 commented on Jan 25, 2025 • 0 new comments

• (fish-speech v1.5) bigger real time factor on short texts

  #744 commented on Jan 26, 2025 • 0 new comments

• while training full or warnings and errors, the weights are not loaded

  #671 commented on Jan 26, 2025 • 0 new comments

• Webui Display Incomplete

  #840 commented on Jan 26, 2025 • 0 new comments

• Bug when running api_server for a while

  #787 commented on Jan 27, 2025 • 0 new comments

• Error when clicking on generate in web ui page

  #779 commented on Jan 27, 2025 • 0 new comments

• Stress on the vowel in Russian language.

  #791 commented on Jan 27, 2025 • 0 new comments

• [BUG] Normal LoRa finetune: Error(s) in loading state_dict for TextToSemantic

  #479 commented on Jan 28, 2025 • 0 new comments

• How to continue training with finetune? What are the steps to continue training

  #843 commented on Jan 28, 2025 • 0 new comments

• Fine-tuning without LoRA

  #832 commented on Jan 28, 2025 • 0 new comments

• Newest Update seems to have broken webui/manage.py

  #825 commented on Jan 29, 2025 • 0 new comments

• When I click Generate Audio, it says “Error”

  #795 commented on Jan 30, 2025 • 0 new comments

• 执行构建agent代码的时候报错如下：Qwen2TokenizerFast has no attribute "get _token_id" . Did you mean:"sep_token_id"

  #712 commented on Jan 30, 2025 • 0 new comments