x-lance / voiceflow-tts Goto Github PK

This code does not work.

diffnet = DiffSingerNet()

x = torch.randn(2, 80, 10)
x_mask = torch.ones(2, 1, 10)
t = torch.tensor([1])
mu = torch.randn(2, 80, 10)

diffnet(x, x_mask, mu, t)

The following code works.

diffnet = DiffSingerNet()

x = torch.randn(2, 80, 10)
x_mask = torch.ones(2, 1, 10)
t = torch.tensor([1])
mu = torch.randn(2, 128, 10)

diffnet(x, x_mask, mu, t)

"cd model/monotonic_align
python setup.py build_ext --inplace"
wonder which gcc version when compile this code

Hi author, I attempt to train VoiceFlow in aishell3 dataset, but some noise appeared in synthesized audio.
Maybe it because of english vocoder?

Hello! I'm working on building my own dataset. Could you give me an example of Python code that generates phoneme sequences (text) and their corresponding durations (phn_duration).

Hi, thanks for your great work. I notice that you add a small gaussian noise when sampling x_t in CFM:

mu_t = t_unsqueeze * x1 + (1 - t_unsqueeze) * x0  # conditional Gaussian mean
sigma_t = self.sigma_min
x = mu_t + sigma_t * torch.randn_like(x1)  # sample p_t(x|x_0, x_1)

This matches the description in your paper. However, I see most other works of rectified flow do not use this sigma_t and they simply use the mean value mu_t as the sampled x_t. I wonder if you have explored on how big influence this sigma_t has on the model performance, and what is the appropriate range of values for sigma_t ? Thanks for your help in advance.

Hello,
I think you missed this text file. Would you provide it?

Thank you for your interesting and valuable research.
I'm having trouble running the following command in terminal:

bash extract_fbank.sh --stage 0 --stop_stage 2 --nj 16

The sampling rate of the original ljspepech dataset is 22050Hz, but an error seems to have occurred in the process of downsampling it to 16kHz.

This is the error message written in 'exp/make_fbank/ljspeech/train/make_fbank_train.*.log'.

`Traceback (most recent call last):
  File "path/to/VoiceFlow-TTS/utils/compute-fbank-feats.py", line 105, in <module>
    main()
  File "/path/to/VoiceFlow-TTS/utils/compute-fbank-feats.py", line 86, in main
    assert rate == args.fs
AssertionError
# Accounting: time=2 threads=1
# Ended (code 1) at Tue 09 Apr 2024 02:01:15 AM UTC, elapsed time 2 seconds`

Thank you.

Thank you for your work and sharing!
It seems VoiceFLow-TTS and MATCHA-TTS（https://github.com/shivammehta25/Matcha-TTS/） are very similar?
What is the main diffences between two methods?
And How about the performace on voice quality, for example prosody, and the inference speed?
Best

Is it possible to calculate density like normalising flows and then use it as KL divergence (like vits) for end2end training?
(i saw the easter eggs, just wanna know your thoughts about this)

How can i get the parse_options.sh ?
$bash extract fbank.sh-stage 0--stop stage 2 --nj 16
extract fbank.sh: line 20:parse options.sh: No such file or directory

Hello,

First of all, thank you for sharing the code!

I was wondering if you have any plans to release a pre-trained model trained on LibriTTS.

How can i get it ?
$bash extract_fbank.sh --stage 0 --stop_stage 2 --nj 16 --sampling_rate 22050
utils/apply-cmvn.py: FileNotFoundError: [Errno 2] No such file or directory: **/cmvn.ark

Hi author, I wonder how many epochs can got some good results, which can distinguish human voices