tacotron | TensorFlow Implementation of Tacotron : A Fully End | Speech library
kandi X-RAY | tacotron Summary
kandi X-RAY | tacotron Summary
A TensorFlow Implementation of Tacotron: A Fully End-to-End Text-To-Speech Synthesis Model
Support
Quality
Security
License
Reuse
Top functions reviewed by kandi - BETA
- Get a batch of data
- Load audio data
- Load the vocab
- Normalize text
- Synthesize the graph
- Calculates the maximum likelihood of a spectrogram
- Invert a spectrogram
- Convert mag to wav format
- 2D decoder
- Conv1D convolutional convolutions
- 1D convolutional layer
- Batch norm
- Evaluate the model
- Load spectrogram from fpath
- Load spectrograms from a file
- First layer
- Attention decoder
- Transformer encoder
- Create prenet layer
- Plot the alignment
tacotron Key Features
tacotron Examples and Code Snippets
Tacotron-2
├── datasets
├── en_UK (0)
│ └── by_book
│ └── female
├── en_US (0)
│ └── by_book
│ ├── female
│ └── male
├── LJSpeech-1.1 (0)
│ └── wavs
├── logs-Tacotr
Tacotron-2
├── datasets
├── LJSpeech-1.1 (0)
│ └── wavs
├── logs-Tacotron (2)
│ ├── mel-spectrograms
│ ├── plots
│ ├── pretrained
│ └── wavs
├── papers
├── tacotron
│ ├── models
Tacotron-2
├── datasets
├── LJSpeech-1.1 (0)
│ └── wavs
├── logs-Tacotron (2)
│ ├── mel-spectrograms
│ ├── plots
│ ├── pretrained
│ └── wavs
├── papers
├── tacotron
│ ├── models
Community Discussions
Trending Discussions on tacotron
QUESTION
I'm quite new to AI and I'm currently developing a model for non-parallel voice conversions. One confusing problem that I have is the use of vocoders.
So my model needs Mel spectrograms as the input and the current model that I'm working on is using the MelGAN vocoder (Github link) which can generate 22050Hz Mel spectrograms from raw wav files (which is what I need) and back. I recently tried WaveGlow Vocoder (PyPI link) which can also generate Mel spectrograms from raw wav files and back.
But, in other models such as, WaveRNN , VocGAN , WaveGrad There's no clear explanation about wav to Mel spectrograms generation. Do most of these models don't require the wav to Mel spectrograms feature because they largely cater to TTS models like Tacotron? or is it possible that all of these have that feature and I'm just not aware of it?
A clarification would be highly appreciated.
...ANSWER
Answered 2022-Feb-01 at 23:05Check e.g. this part of the MelGAN code: https://github.com/descriptinc/melgan-neurips/blob/master/mel2wav/modules.py#L26
Specifically, the Audio2Mel
module simply uses standard methods to create log-magnitude mel spectrograms like this:
- Compute the STFT by applying the Fourier transform to windows of the input audio,
- Take the magnitude of the resulting complex spectrogram,
- Multiply the magnitude spectrogram by a mel filter matrix. Note that they actually get this matrix from
librosa
! - Take the logarithm of the resulting mel spectrogram.
Your confusion might stem from the fact that, usually, authors of Deep Learning papers only mean their mel-to-audio "decoder" when they talk about "vocoders" -- the audio-to-mel part is always more or less the same. I say this might be confusing since, to my understanding, the classical meaning of the term "vocoder" includes both an encoder and a decoder.
Unfortunately, these methods will not always work exactly in the same manner as there are e.g. different methods to create the mel filter matrix, different padding conventions etc.
For example, librosa.stft
has a center
argument that will pad the audio before applying the STFT, while tensorflow.signal.stft
does not have this (it would require manual padding beforehand).
An example for the different methods to create mel filters would be the htk
argument in librosa.filters.mel
, which switches between the "HTK" method and "Slaney". Again taking Tensorflow as an example, tf.signal.linear_to_mel_weight_matrix
does not support this argument and always uses the HTK method. Unfortunately, I am not familiar with torchaudio
, so I don't know if you need to be careful there, as well.
Finally, there are of course many parameters such as the STFT window size, hop length, the frequencies covered by the mel filters etc, and changing these relative to what a reference implementation used may impact your results. Since different code repositories likely use slightly different parameters, I suppose the answer to your question "will every method do the operation(to create a mel spectrogram) in the same manner?" is "not really". At the end of the day, you will have to settle for one set of parameters either way...
Bonus: Why are these all only decoders and the encoder is always the same?The direction Mel -> Audio is hard. Not even Mel -> ("normal") spectrogram is well-defined since the conversion to mel spectrum is lossy and cannot be inverted. Finally, converting a spectrogram to audio is difficult since the phase needs to be estimated. You may be familiar with methods like Griffin-Lim (again, librosa has it so you can try it out). These produce noisy, low-quality audio. So the research focuses on improving this process using powerful models.
On the other hand, Audio -> Mel is simple, well-defined and fast. There is no need to define "custom encoders".
Now, a whole different question is whether mel spectrograms are a "good" encoding. Using methods like variational autoencoders, you could perhaps find better (e.g. more compact, less lossy) audio encodings. These would include custom encoders and decoders and you would not get away with standard librosa functions...
QUESTION
I have audio data of around 20K files with a sampling rate of 44100Khz. I'm using the data for training the Text-to-Speech Tacotron model. However, the parameters configured for successful training are as below: Hence I need to downsample the data to 22.5Khz.
...ANSWER
Answered 2021-Apr-19 at 10:49It looks like your model requires a Mel spectrogram as input, which has been generated with the given parameters. I.e. sr=22050
, hop_length=...
etc. These parameters have nothing to do with downsampling.
To create a suitable spectrogram, do something like this:
QUESTION
I'm trying to run tacotron2 on docker
within Ubuntu WSL2 (v.20.04)
on Win10 2004
build. Docker is installed and running and I can run hello world
successfully.
(There's a nearly identical question here, but nobody has answered it.)
When I try to run docker build -t tacotron-2_image docker/
I get the error:
unable to prepare context: unable to evaluate symlinks in Dockerfile path: lstat /home/nate/docker/Dockerfile: no such file or directory
So then I navigated in bash to where docker is installed (/var/lib/docker
) and tried to run it there, and got the same error. In both cases I created a docker
directory, but kept getting that error in all cases.
How can I get this to work?
...ANSWER
Answered 2020-Aug-16 at 16:52As mentioned here, the error might have nothing to do with "symlinks", and everything with the lack of Dockerfile
, which should be in the Tacotron-2/docker
folder.
docker build
does mention:
The docker build command builds Docker images from a Dockerfile and a “context”.
A build’s context is the set of files located in the specifiedPATH
or URL.
In your case, docker build -t tacotron-2_image docker/
is supposed to be executed in the path you have cloned the Rayhane-mamah/Tacotron-2
repository.
To be sure, you could specify said Dockerfile
, but that should not be needed:
QUESTION
I was earlier able to browse the github repo at https://github.com/r9y9/Tacotron-2/blob/master/wavenet_vocoder/models/wavenet.py easily in browser, so that when I put cursor on top of jResidualConv1dGLU at Line84, it'd highlight and let me click on "Definition" and "References" of class ResidualConv1dGLU
.
But I used the same repo in the same browser today, and it doesn't do anything. It doesn't highlight ResidualConv1dGLU
or show links for Definition/References of it. It's as if it doesn't know that it's a class.
Is there some default setting needed to enable that? What am I missing?
PS: (It was working a few days ago, so I am not sure what changed in just a few days)
...ANSWER
Answered 2020-Jun-24 at 06:09What might have changed yesteraday (June 23, 2020) is "Design updates to repositories and GitHub UI"
Try and make sure to clear the cache of your browser and reload everything.
That being said, when clicking on "Jump to", I see:
"Code navigation not available for this commit", which is expected for a fork.
But I see the same issue on the original repository Rayhane-mamah/Tacotron-2
.
Those repositories needs to be re-scanned by GitHub, as I mentioned here.
QUESTION
I am trying to implement Tacotron speech synthesis with Tensorflow in Google Colab using this code form a repo in Github, below is my code and working good till the step of using localhost server, how I can to run a localhost server in a notebook in Google Colab?
My code:
...ANSWER
Answered 2020-Mar-09 at 02:50You can do this by using tools like ngrok or remote.it
They give you a URL that you can access from any browser to access your web server running on 8888
Example 1: Tunneling tensorboard running on
Community Discussions, Code Snippets contain sources that include Stack Exchange Network
Vulnerabilities
No vulnerabilities reported
Install tacotron
You can use tacotron like any standard Python library. You will need to make sure that you have a development environment consisting of a Python distribution including header files, a compiler, pip, and git installed. Make sure that your pip, setuptools, and wheel are up to date. When using pip it is generally recommended to install packages in a virtual environment to avoid changes to the system.
Support
Reuse Trending Solutions
Find, review, and download reusable Libraries, Code Snippets, Cloud APIs from over 650 million Knowledge Items
Find more librariesStay Updated
Subscribe to our newsletter for trending solutions and developer bootcamps
Share this Page