diff --git a/WORKFLOW.md b/WORKFLOW.md new file mode 100644 index 0000000..a953b8f --- /dev/null +++ b/WORKFLOW.md @@ -0,0 +1,23 @@ + +## Setup +- clone the repo + +`git clone https://github.com/agaralabs/tacotron2` +- cd to `tacotron2` copy models from wolverine: + +`scp wolverine:/home/ubuntu/tacotron2/{checkpoint_15000,waveglow_256channels.pt} ./` + +`scp wolverine:/home/ubuntu/tacotron2/waveglow ./` + +**Wolverine Details:** +``` +Host wolverine + Hostname 54.71.137.17 + User ubuntu + IdentityFile ~/.ssh/id_hip_ml +``` +install the dependencies +`pip install requirements.txt` + +## Running: +`python final.py` diff --git a/demo.wav b/demo.wav deleted file mode 100755 index 54d1dbc..0000000 Binary files a/demo.wav and /dev/null differ diff --git a/final.py b/final.py index ccaf952..b27ffa4 100644 --- a/final.py +++ b/final.py @@ -18,7 +18,7 @@ from text import text_to_sequence # from denoiser import Denoiser import os import soundfile as sf -# import pyaudio +import pyaudio import time sys.path.append('waveglow/') @@ -35,10 +35,6 @@ waveglow.eval() for k in waveglow.convinv: k.float() -# audio_interface = pyaudio.PyAudio() -# # _audio_stream = audio_interface.open(format=pyaudio.paFloat32,channels=1, rate=22050,output=True) -# _audio_stream = audio_interface.open(format=pyaudio.paInt16,channels=1, rate=16000,output=True) - # https://github.com/NVIDIA/waveglow/issues/127 for m in waveglow.modules(): if 'Conv' in str(type(m)): @@ -72,12 +68,11 @@ def speech(t): def main(): - speech( - ('I understand your frustration and disappointment. I am sorry that' - ' its happening and I would like to help prevent it in the future. ' - 'What style of diapers did you buy? For instance, was it the ' - 'snugglers, pull ups or baby dry.')) - + data = speech('Hi I am Sia How may I help you today'.lower()) + audio_interface = pyaudio.PyAudio() + _audio_stream = audio_interface.open(format=pyaudio.paInt16,channels=1, rate=16000,output=True) + _audio_stream.write(data) + import pdb; pdb.set_trace() if __name__ == '__main__': main()