is2ai/kazakh_tts

An expanded version of the previously released Kazakh text-to-speech (KazakhTTS) synthesis corpus. In KazakhTTS2, the overall size has increased from 93 hours to 271 hours, the number of speakers has risen from two to five (three females and two males), and the topic coverage has been diversified.

kazakh_tts's Issues

Where to get the models from README.md?

Hello, I want to test your repo on my data to make text2speach, but I have an issue

I have installed all properly, but I do not understand where to get following models:

## specify the path to vocoder's checkpoint, i.e 
vocoder_checkpoint="exp/vocoder/checkpoint-400000steps.pkl" 

## specify path to the main model(transformer/tacotron2/fastspeech) and its config file 
config_file = "exp/tts_train_raw_char/config.yaml" 
model_path = "exp/tts_train_raw_char/train.loss.ave_5best.pth"

Can you please provide links where to download these models?

Thank you very much!

Waiting for your reply!

What should be input to the vocoder.inference() function?

Hello, I'm having trouble testing the TTS script synthesize.py.

Problems arose with the execution of these lines:
_, c_mel, *_ = text2speech(sample_text.lower())
wav = vocoder.inference(c_mel).

The c_mel variable is assigned a string, which subsequently results in an error.

Tell me, please, what tensor should be fed to the input of the vocoder.inference() function?

Dataset request

Dear IS2AI,
In page https://issai.nu.edu.kz/ru/tts-rus/ you say that dataset is available upon request. I've wrote request to your contact email [email protected] several days before but haven't got reply.

Could you please provide answer on my request or provide access to dataset in response to this issue?

Thanks a lot

Pretrained model without CUDA

Hi,
I would like test your TTS and use it without CUDA if it's possible.
Could you give me an example of synthesizer with pretrained model and without cuda?
Thanks

The website https://issai.nu.edu.kz/ cannot be opened.

The website https://issai.nu.edu.kz/ cannot be opened.

Web API for TTS

Hello. Thanks for this project! I was wondering is there any web API for Kazakh TTS? (send text to the endpoint, get audio)

При сборке ругется на библиотеку torch.

Прошу выложить tts файл в примерах. Я пологаю вот тут используются ваши tts файлы: https://ttsfree.com/text-to-speech/kazakh-kazakhstan#google_vignette

Google form to access the dataset is not working

Hello,

I would like to download this dataset and have tried filling out the Google form: https://docs.google.com/forms/d/e/1FAIpQLSf4vlv2NAV2dA8QL2V_uQZHOUENY6SR87n_9xToSEHX5oylVA/viewform

The form does not seem to accept answers given for "Brief Purpose"

Pretrained models not available

Hi,

the linked pretrained models like https://issai.nu.edu.kz/wp-content/uploads/2021/04/kaztts_male1_tacotron2_train.loss.ave.zip can't be downloaded. The links forward to the main page.

greetings