File size: 2,262 Bytes
950142f 8a7a5ec 950142f 8a7a5ec 950142f 8a7a5ec 950142f 8a7a5ec 950142f |
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 |
import gradio as gr
import torch
from transformers import VitsModel, VitsTokenizer
# --- 1. Load Model and Tokenizer ---
# NOTE: Switched to a compatible model that has the correct file structure.
print("Loading facebook/mms-tts-eng model and tokenizer...")
model_id = "facebook/mms-tts-eng"
model = VitsModel.from_pretrained(model_id)
tokenizer = VitsTokenizer.from_pretrained(model_id)
print("Model and tokenizer loaded successfully.")
# --- 2. Define the Speech Synthesis Function ---
def synthesize_speech(text):
"""
Converts text to speech using the selected TTS model.
"""
# Tokenize the input text. The `return_tensors="pt"` part formats it for PyTorch.
inputs = tokenizer(text, return_tensors="pt")
# Generate the audio waveform.
# We use torch.no_grad() to speed up inference as we aren't training the model.
with torch.no_grad():
waveform = model(**inputs).waveform
# The output is a PyTorch tensor. Convert it to a NumPy array.
# .squeeze() removes any extra single dimensions.
waveform_numpy = waveform.cpu().numpy().squeeze()
# Get the sampling rate from the model's configuration.
sampling_rate = model.config.sampling_rate
# Return the sampling rate and waveform as a tuple for the Gradio Audio component.
return (sampling_rate, waveform_numpy)
# --- 3. Build the Gradio Interface ---
demo = gr.Interface(
fn=synthesize_speech,
inputs=gr.Textbox(
label="Text to Synthesize",
info="Enter the text you want to convert to speech.",
value="Hello, this is a demonstration of the Facebook MMS text to speech model."
),
outputs=gr.Audio(
label="Synthesized Audio",
type="numpy" # The function returns a NumPy array
),
title="🗣️ MMS Text-to-Speech (English)",
description="A Gradio app to run the `facebook/mms-tts-eng` model for text-to-speech conversion.",
examples=[
["The quick brown fox jumps over the lazy dog."],
["To be, or not to be, that is the question."],
["Artificial intelligence will shape our future in profound ways."]
],
cache_examples=True # Cache results for faster demo
)
# --- 4. Launch the App ---
if __name__ == "__main__":
demo.launch() |