File size: 1,014 Bytes
da1f30f 616dbaa e171f13 e4bf055 da1f30f 8b2b538 e171f13 616dbaa e171f13 616dbaa e171f13 df81b93 8192711 e171f13 |
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 |
import gradio as gr
import numpy as np
# Load spectrogram generator
from nemo.collections.tts.models import FastPitchModel
spec_generator = FastPitchModel.from_pretrained(model_name="inOXcrm/German_multispeaker_FastPitch_nemo")
# Load Vocoder
from nemo.collections.tts.models import HifiGanModel
model = HifiGanModel.from_pretrained(model_name="tts_de_hui_hifigan_ft_fastpitch_multispeaker_5")
# Generate audio
def generate_audio(speaker_id, input_txt):
sr=44100
parsed = spec_generator.parse(input_txt)
spectrogram = spec_generator.generate_spectrogram(tokens=parsed, speaker=int(speaker_id))
audio = model.convert_spectrogram_to_audio(spec=spectrogram)
audio = audio.to('cpu').detach().numpy()[0]
audio = audio / np.abs(audio).max()
return (sr, audio)
gr.Interface(
generate_audio,
[
gr.Textbox(type="text", value=1, label="Speaker ID (1-5)"),
gr.Textbox(type="text", value="Hallo, wie geht es ihnen?", label="Input Text")
],
"audio",
).launch()
|