Spaces:
Running
Running
File size: 3,587 Bytes
ce18f8b 2d0bddc ce18f8b db34208 2d0bddc ce18f8b 2d0bddc ce18f8b db34208 ce18f8b 2d0bddc ce18f8b 2d0bddc ce18f8b db34208 2d0bddc db34208 ce18f8b 2d0bddc ce18f8b db34208 ce18f8b |
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 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 |
#######################################################################################
#
# MIT License
#
# Copyright (c) [2025] [[email protected]]
#
# Permission is hereby granted, free of charge, to any person obtaining a copy
# of this software and associated documentation files (the "Software"), to deal
# in the Software without restriction, including without limitation the rights
# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
# copies of the Software, and to permit persons to whom the Software is
# furnished to do so, subject to the following conditions:
#
# The above copyright notice and this permission notice shall be included in all
# copies or substantial portions of the Software.
#
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
# SOFTWARE.
#
#######################################################################################
# This file implements an API endpoint for the Italian Kokoro Text-to-Speech (TTS) system.
# It provides functionality to generate TTS audio from input Italian text using the Kokoro voice model.
# Source code is based on or inspired by several projects.
# For more details and proper attribution, please refer to the following resources:
#
# - [Kokoro] - [https://github.com/hexgrad/kokoro]
# - [Misaki] - [https://github.com/hexgrad/misaki]
# - [Kokoro-82M] - [https://huggingface.co/hexgrad/Kokoro-82M]
# - [Kokoro-onnx] - [https://github.com/thewh1teagle/kokoro-onnx]
import os
import gradio as gr
from misaki import espeak
from misaki.espeak import EspeakG2P
from kokoro_onnx import Kokoro
from huggingface_hub import snapshot_download
KOKORO_REPO_ID = "leonelhs/kokoro-thewh1teagle"
VOICES = {
'🚺 Sara':'if_sara',
'🚹 Nicola':'im_nicola'
}
snapshot = snapshot_download(repo_id=KOKORO_REPO_ID)
# Misaki G2P with espeak-ng fallback
fallback = espeak.EspeakFallback(british=False)
g2p = EspeakG2P(language="it")
# Kokoro
model_path = os.path.join(snapshot, "kokoro-v1.0.onnx")
voices_path = os.path.join(snapshot, "voices-v1.0.bin")
kokoro = Kokoro(model_path, voices_path)
def predict(text, voice='ef_dora', speed=1):
"""
Generate speech audio from italian text input.
Parameters:
text (string): The text to be converted into speech.
voice (string): The selected male of female voice profile (specific voice ID).
speed (float): The speaking rate multiplier (e.g., 1.0 = normal speed, 0.8 = slower, 1.2 = faster).
Returns:
path: File path to the generated audio speech.
"""
phonemes, _ = g2p(text)
samples, sample_rate = kokoro.create(phonemes, voice, speed, is_phonemes=True)
return sample_rate, samples
app = gr.Interface(
predict,
[
gr.Textbox(label='Input Text'),
gr.Dropdown(list(VOICES.items()), value='ef_dora', label='Voice'),
gr.Slider(minimum=0.5, maximum=2, value=1, step=0.1, label='Speed')
],
gr.Audio(label='Output Audio', interactive=False, streaming=False, autoplay=True),
description="Kokoro TTS 🇮🇹 API Endpoint",
)
app.launch(share=False, debug=True, show_error=True, mcp_server=True)
app.queue()
|