9 Issues closed by 4 people

• [Bug] Streaming doesn't work

  #4011 closed Nov 11, 2024

• [Bug] ValueError: Can't infer missing attention mask on `mps` device. Please provide an `attention_mask` or use a different device.

  #3758 closed Nov 11, 2024

• Can't install TTL on Windows 11: Could not build wheels for TTS

  #3722 closed Nov 10, 2024

• [Feature request]

  #3831 closed Nov 10, 2024

• [Feature request] Batch inference onnx Model

  #3814 closed Nov 10, 2024

• [Feature request] Can we add the batch inference or batch decoding for XTTS

  #3776 closed Nov 10, 2024

• [Bug] list_speaker_idx issue for bark model

  #3823 closed Nov 10, 2024

• window 11 pip install TTS,Display installation successful，But I can't quote it

  #3822 closed Nov 10, 2024

• [Bug] speedy_speech erroring on short inputs

  #3554 closed Nov 10, 2024

1 Issue opened by 1 person

• [Bug] installation failure AttributeError: 'dict' object has no attribute '__NUMPY_SETUP__'

  #4046 opened Nov 6, 2024

23 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.

• [Bug] fugashi.Tagger causes pickling error during multiprocessing in tokenizer (Japanese)

  #4031 commented on Nov 10, 2024 • 0 new comments

• Searching for a coqui tool, help please !

  #4020 commented on Nov 10, 2024 • 0 new comments

• [Bug] Input and parameter tensors are not at the same device. How to point the input tensor to cuda:2?

  #3985 commented on Nov 10, 2024 • 0 new comments

• [Bug] start word is often skipped

  #4016 commented on Nov 10, 2024 • 0 new comments

• [Bug] Failed building wheel

  #3828 commented on Nov 10, 2024 • 0 new comments

• [ I have Vietnamese voice data] Please provide support for Vietnamese

  #4007 commented on Nov 10, 2024 • 0 new comments

• [Feature request] Possibility of using a fixed seed for inference in XTTS V2

  #4001 commented on Nov 10, 2024 • 0 new comments

• [Bug] mps doesn't seem to work

  #3998 commented on Nov 10, 2024 • 0 new comments

• [Bug] AttributeError: 'int' object has no attribute 'device'

  #3996 commented on Nov 10, 2024 • 0 new comments

• [Bug] SSLCertVerificationError with multilingual voice conversion

  #3990 commented on Nov 10, 2024 • 0 new comments

• [Bug] loss is NaN when fine-tuning XTTS_v2!

  #3988 commented on Nov 10, 2024 • 0 new comments

• [Bug] TTS.trainer isn't working

  #3984 commented on Nov 10, 2024 • 0 new comments

• [Bug] vctk-vits convert into ONNX error

  #3979 commented on Nov 10, 2024 • 0 new comments

• [Feature request] pronounciation, cadence and nuances in XTTS v2...

  #3764 commented on Nov 10, 2024 • 0 new comments

• [Bug] RuntimeError: shape '[64, 31, -1]' is invalid for input of size 8064

  #3798 commented on Nov 10, 2024 • 0 new comments

• why xtts v2 inference time used RAM double(or more 3x) then GPU or VRAM

  #3976 commented on Nov 10, 2024 • 0 new comments

• [Feature request] Transformers 4.43+ Support

  #3974 commented on Nov 10, 2024 • 0 new comments

• Can't read Bengali year ১৯৫৪ সাল। কালো রাত। [Bug]

  #3815 commented on Nov 10, 2024 • 0 new comments

• Do you support Vietnamese ?

  #3817 commented on Nov 10, 2024 • 0 new comments

• [Bug] Training XTTSv2 with DDP leads to weird training lags

  #3807 commented on Nov 10, 2024 • 0 new comments

• Distributed training

  #3802 commented on Nov 10, 2024 • 0 new comments

• [Bug] on large text with device=cpu, tts_to_file will throw RuntimeError bad allocation

  #3800 commented on Nov 11, 2024 • 0 new comments

• Fix wrong references in documentation

  #3963 commented on Nov 9, 2024 • 0 new comments