File size: 1,670 Bytes
f845b05 944dedf 4eb15f6 944dedf 791253b 944dedf 418b839 944dedf f8bf4b8 f845b05 944dedf 21c111d |
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
import wave
import numpy as np
from io import BytesIO
from huggingface_hub import hf_hub_download
from piper import PiperVoice # Adjust import as per your project structure
#file_path = hf_hub_download("rhasspy/piper-voices", "en_GB-alan-medium.onnx")
def synthesize_speech(text):
# Load the PiperVoice model and configuration
# model_path = "en_GB-alan-medium.onnx" # this is for loading local model
# config_path = "en_GB-alan-medium.onnx.json" # for loading local json
model_path = hf_hub_download(repo_id="rhasspy/piper-voices", filename="en/en_GB/alan/medium/en_GB-alan-medium.onnx")
config_path = hf_hub_download(repo_id="rhasspy/piper-voices", filename="en/en_GB/alan/medium/en_GB-alan-medium.onnx.json")
voice = PiperVoice.load(model_path, config_path)
# Create an in-memory buffer for the WAV file
buffer = BytesIO()
with wave.open(buffer, 'wb') as wav_file:
wav_file.setframerate(voice.config.sample_rate)
wav_file.setsampwidth(2) # 16-bit
wav_file.setnchannels(1) # mono
# Synthesize speech
voice.synthesize(text, wav_file)
# Convert buffer to NumPy array for Gradio output
buffer.seek(0)
audio_data = np.frombuffer(buffer.read(), dtype=np.int16)
return audio_data.tobytes()
# Create a Gradio interface with labels
iface = gr.Interface(
fn=synthesize_speech,
inputs=gr.Textbox(label="Input Text"),
outputs=[gr.Audio(label="Synthesized Speech")],
title="Text to Speech Synthesizer",
description="Enter text to synthesize it into speech using PiperVoice.",
allow_flagging="never"
)
# Run the app
iface.launch()
|