Spaces:
Sleeping
Sleeping
File size: 1,450 Bytes
810b795 4d1dde6 b2605d1 4d1dde6 b2605d1 4d1dde6 810b795 b2605d1 810b795 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 |
import gradio as gr
from transformers import pipeline
from datasets import load_dataset
import soundfile as sf
import torch
import os
os.environ['TRANSFORMERS_CACHE'] = '.cache'
print ("----- setting up pipeline -----")
synthesiser = pipeline("text-to-speech", "microsoft/speecht5_tts")
print ("----- setting up dataset -----")
embeddings_dataset = load_dataset("Matthijs/cmu-arctic-xvectors", split="validation")
speaker_embedding = torch.tensor(embeddings_dataset[7306]["xvector"]).unsqueeze(0)
# You can replace this embedding with your own as well.
print ("----- synthetizing audio -----")
#speech = synthesiser("Hello, my dog is cooler than you!", forward_params={"speaker_embeddings": speaker_embedding})
#sf.write("speech.wav", speech["audio"], samplerate=speech["sampling_rate"])
def greet(name):
return "Hello " + name + "!!"
def synthesise_audio(text, forward_params=None):
speech = synthesiser(text, forward_params={"speaker_embeddings": speaker_embedding})
sf.write("speech.wav", speech["audio"], samplerate=speech["sampling_rate"])
return "speech.wav"
#demo = gr.Interface(fn=greet, inputs="text", outputs="text", description="----- TTS Testing -----")
demo = gr.Interface(fn=synthesise_audio,
inputs="text",
outputs="audio",
description="----- manuai Text To Speech generator -----",
allow_flagging = False)
demo.launch()
|