File size: 2,280 Bytes
846d465 9ec2680 6ee5bb1 846d465 9ec2680 846d465 9ec2680 846d465 9ec2680 846d465 9ec2680 6ee5bb1 aff15ad 9ec2680 aff15ad 6ee5bb1 |
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 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 |
import tempfile
from typing import Optional
import gradio as gr
import numpy as np
from TTS.utils.manage import ModelManager
from TTS.utils.synthesizer import Synthesizer
MODEL_NAMES = [
# "en/ek1/tacotron2",
"en/ljspeech/tacotron2-DDC",
# "en/ljspeech/tacotron2-DDC_ph",
# "en/ljspeech/glow-tts",
# "en/ljspeech/tacotron2-DCA",
# "en/ljspeech/speedy-speech-wn",
# "en/ljspeech/vits",
# "en/vctk/sc-glow-tts",
# "en/vctk/vits",
# "en/sam/tacotron-DDC",
# "es/mai/tacotron2-DDC",
"fr/mai/tacotron2-DDC",
"zh-CN/baker/tacotron2-DDC-GST",
"nl/mai/tacotron2-DDC",
"de/thorsten/tacotron2-DCA",
# "ja/kokoro/tacotron2-DDC",
]
MODELS = {}
manager = ModelManager()
for MODEL_NAME in MODEL_NAMES:
print(f"downloading {MODEL_NAME}")
model_path, config_path, model_item = manager.download_model(f"tts_models/{MODEL_NAME}")
vocoder_name: Optional[str] = model_item["default_vocoder"]
vocoder_path = None
vocoder_config_path = None
if vocoder_name is not None:
vocoder_path, vocoder_config_path, _ = manager.download_model(vocoder_name)
synthesizer = Synthesizer(
model_path, config_path, None, vocoder_path, vocoder_config_path,
)
MODELS[MODEL_NAME] = synthesizer
def tts(text: str, model_name: str):
print(text, model_name)
synthesizer = MODELS.get(model_name, None)
if synthesizer is None:
raise NameError("model not found")
wavs = synthesizer.tts(text)
# output = (synthesizer.output_sample_rate, np.array(wavs))
# return output
with tempfile.NamedTemporaryFile(suffix=".wav", delete=False) as fp:
synthesizer.save_wav(wavs, fp)
return fp.name
iface = gr.Interface(
fn=tts,
inputs=[
gr.inputs.Textbox(
label="Input",
default="Hello, how are you?",
),
gr.inputs.Radio(
label="Pick a TTS Model",
choices=MODEL_NAMES,
),
],
outputs=gr.outputs.Audio(label="Output"),
title="🐸💬 - Coqui TTS",
theme="huggingface",
description="🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production",
article="more info at https://github.com/coqui-ai/TTS",
)
iface.launch()
|