merlin

merlin copied to clipboard

How to use festival as front-end

1

i have trained the arctic voice and i want to setup a TTS in my laptop i have to use festival as frontend and World vocoder along with merlin i...

ratz-creator

Why is that when it could synthesize voice for same sampling rate data set, and next time when I reduce data size and try training it throws up dimensions mismatch...

A-d-DASARE

unable to train the duration model

2

I am using merlin in google colaboratory and i have installed python3.6 version as well as all the requirements and when i am training the duration model I am getting...

baniyacoder

Parallel forced alignment

13

This PR solves "ERROR [+7031] during forced_alignment.py" as dicussed in #293. List of changes: - Alignment in parallel on multiple chunks of data (checks the "DNN_NUM_PARALLEL" environment variable and uses...

m-toman

Step 2: Preparing labels... Making directories Copying relevant script files Generating clunits specific voice and build files Set up for cmu_us_myownvoice complete Copying general files Copying intonation files Copying duration...

fiantonumber1

IndexError: index 0 is out of bounds for axis 0 with size 0

10

Get this error after runned `time ./run_full_voice.sh`: ``` 2019-03-18 02:18:11,773 INFO param_generation: processing 1 of 1: /data/user_data/external_projects/text-to-speech/merlin/egs/slt_arctic/s1/experiments/slt_arctic_full/test_synthesis/wav/test_me.cmp Traceback (most recent call last): File "/data/user_data/external_projects/text-to-speech/merlin/src/run_merlin.py", line 1320, in main_function(cfg) File "/data/user_data/external_projects/text-to-speech/merlin/src/run_merlin.py",...

mrgloom

Issue in creating labels from utts

1

I'm getting following error, when trying to build labels from festival utts. **" SIOD ERROR: unbound variable : eof gawk: fatal: cannot open file `./full_context_labels/labels//tmp' for reading (No such file...

priyanthini

I'm developing a TTS for Tamil usinng merlin. I have completed upto training duration model. Now error comes in 6th step, train_acoustic_model step. Error comes as follows : **2020-01-21 12:52:07,108...

priyanthini

python dependencies

2

Hello I am trying to build merlin tts. Until now I have succesfully compiled all tools. When I install python dependencies such as: pip install numpy scipy matplotlib lxml theano...

nipppas

Hi, I tried to create linguistic feature for mandarin follow this recipe: egs/mandarin_voice I noticed that in the question file, mandarin used only L-\*/C-\*/R-\* phones, while other locale used all...

OnceJune