File size: 1,103 Bytes
e666f63 b5129f6 e5dfbf9 e666f63 3a1e5e2 9dd9a4a b5129f6 598e0b4 9dd9a4a b5129f6 f32ac60 b5129f6 e10c285 |
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 |
from transformers import SpeechT5Processor, SpeechT5ForTextToSpeech, SpeechT5HifiGan
from datasets import load_dataset
import torch
import soundfile as sf
from datasets import load_dataset
from IPython.display import Audio
import streamlit as st
st.title("TTS-App")
text = st.text_input('Donnez votre text à prédire: ', ' ')
processor = SpeechT5Processor.from_pretrained("microsoft/speecht5_tts")
model = SpeechT5ForTextToSpeech.from_pretrained("microsoft/speecht5_tts")
vocoder = SpeechT5HifiGan.from_pretrained("microsoft/speecht5_hifigan")
# read input text from file
inputs = processor(text=text, return_tensors="pt")
embeddings_dataset = load_dataset("Matthijs/cmu-arctic-xvectors", split="validation")
speaker_embeddings = torch.tensor(embeddings_dataset[7306]["xvector"]).unsqueeze(0)
speech = model.generate_speech(inputs["input_ids"], speaker_embeddings, vocoder=vocoder)
#sf.write("VocalEminem.wav", speech.numpy(), samplerate=16000)
sf.write("speech.wav", speech.numpy(), samplerate=16000)
#audio_path = "VocalEminem.wav"
audio_path="speech.wav"
Audio(audio_path)
st.audio(audio_path) |