tacotron
tacotron copied to clipboard
keithito
A TensorFlow implementation of Google's Tacotron speech synthesis with pre-trained model (unofficial)
Traceback (most recent call last): File "C:\Users\72970\Anaconda3\envs\tensorflow\lib\concurrent\futures\process.py", line 175, in _process_worker r = call_item.fn(*call_item.args, **call_item.kwargs) File "C:\Users\72970\Desktop\1\datasets\thchs30.py", line 74, in _process_utterance mel_spectrogram = audio.melspectrogram(wav).astype(np.float32) File "C:\Users\72970\Desktop\1\util\audio.py", line 66, in melspectrogram...
I have tried training on Emotion Dataset which have multiple emotions and same text. So while training at every checkpoint it generates an audio file using some text (dont know...
I'm working for the Bengali language and using `cleaners=transliteration_cleaners`. But most of the cases it gives wrong phoneme representation for Bengali. Can I use **IPA** [1]? [1] https://en.wikipedia.org/wiki/International_Phonetic_Alphabet
Hello everyone! Do you guys have any plans for SSML support for the Tacotron? It would be cool to be able to set specific pause duration, stress-positions and so on!
Hello! Thank you for the sharing your implementation of the tacotron. Your code is well documented, but I still can't completely figure out some things. 1. Could you (or somebody...
@keithito I was able to successfully run the model using the latest implementation from this project on a NVIDIA Jetson TX2 HW with GPU support using CUDA. I used the...
I've updated the `symbols.py` for training Cantonese. I'm using Jyutping representation of transcripts which English characters with numbers(1-6). Jyutping representation ```text wong5 si6 faat3 sang1 zoi6 cat1 sap6 ng5 nin4...
Please help, My GPU is RTX 2070 8GB and I'm running using TF 1.12 with CUDA 9.0 and CuDNN 7.5. When I run the demo_server.py, I got the following error...
hello, my own model in native language was trained based on default hparams.py parameters and LJSpeech dataset standards, but need some improvements: 1. the generated sample has low audio quality...
