app.py

from transformers import pipeline
from datasets import load_dataset
import soundfile as sf
import torch
from IPython.display import Audio
import gradio as gr
synthesiser = pipeline("text-to-speech", "jsbeaudry/haitian_creole_tts_11K")

embeddings_dataset = load_dataset("Matthijs/cmu-arctic-xvectors", split="validation")
speaker_embedding = torch.tensor(embeddings_dataset[7306]["xvector"]).unsqueeze(0)
# You can replace this embedding with your own as well.
def generate_speech(text):
  speech = synthesiser(text, forward_params={"speaker_embeddings": speaker_embedding})
  sf.write("generated_speech.wav", speech["audio"], samplerate=speech["sampling_rate"])
  return "generated_speech.wav"

iface = gr.Interface(
    fn=generate_speech,
    inputs=gr.Textbox(lines=2, placeholder="Enter Haitian Creole text here..."),
    outputs=gr.Audio(label="Generated Speech"),
    title="Haitian Creole Text-to-Speech",
    description="Generate speech from Haitian Creole text using a fine-tuned Text-to-Speech model."
)

iface.launch()


# import gradio as gr
# import torch
# import soundfile as sf
# from IPython.display import Audio
# from transformers import pipeline
# from datasets import load_dataset
# import re

# number_words = {
#     0: "zewo", 1: "en", 2: "de", 3: "twa", 4: "kat", 5: "senk", 6: "sis", 7: "sèt", 8: "uit", 9: "nèf",
#     10: "dis", 11: "onz", 12: "douz", 13: "trez", 14: "katorz", 15: "kenz", 16: "sèz", 17: "dis sèt",
#     18: "dis uit", 19: "dis nèf", 20: "vent", 30: "trant", 40: "karant", 50: "senkant", 60: "swasant",
#     70: "swasant diz", 80: "katreven", 90: "katreven diz", 100: "san", 1000: "mil"
# }

# def number_to_words(number):
#     if number < 20:
#         return number_words[number]
#     elif number < 100:
#         tens, unit = divmod(number, 10)
#         return number_words[tens * 10] + (" " + number_words[unit] if unit else "")
#     elif number < 1000:
#         hundreds, remainder = divmod(number, 100)
#         return (number_words[hundreds] + " san" if hundreds > 1 else "san") + (" " + number_to_words(remainder) if remainder else "")
#     elif number < 1000000:
#         thousands, remainder = divmod(number, 1000)
#         return (number_to_words(thousands) + " mil" if thousands > 1 else "mil") + (" " + number_to_words(remainder) if remainder else "")
#     elif number < 1000000000:
#         millions, remainder = divmod(number, 1000000)
#         return number_to_words(millions) + " milyon" + (" " + number_to_words(remainder) if remainder else "")
#     elif number < 1000000000000:
#         billions, remainder = divmod(number, 1000000000)
#         return number_to_words(billions) + " milya" + (" " + number_to_words(remainder) if remainder else "")
#     else:
#         return str(number)

# def replace_numbers_with_words2(text):
#     def replace(match):
#         number = int(match.group())
#         return number_to_words(number)

#     return re.sub(r'\b\d+\b', replace, text)
# # Function to clean up text using the replacement pairs
# def normalize_text2(text):
#     # Convert to lowercase
#     text = text.lower()

#     # Remove punctuation (except apostrophes)
#     text = re.sub(r'[^\w\s\']', '', text)

#     # Remove extra whitespace
#     text = ' '.join(text.split())

#     return text
# replacements = [
    
#     ("b", "b"), ("d", "d"), ("f", "f"), ("g", "ɡ"), ("h", "h"),
#     ("j", "ʒ"), ("k", "k"), ("l", "l"), ("m", "m"), ("n", "n"),
#     ("p", "p"), ("r", "r"), ("s", "s"), ("t", "t"), ("v", "v"),
#     ("w", "w"), ("y", "y"), ("z", "z"),

#     ("a", "a"), ("e", "e"), ("è", "ɛ"), ("i", "i"), ("o", "o"),
#     ("ò", "ɔ")
# ]

# def cleanup_text2(cleaned_text):
#     for src, dst in replacements:
#         cleaned_text = cleaned_text.replace(src, dst)
#     return cleaned_text

# # Load the text-to-speech pipeline and speaker embedding
# synthesiser = pipeline("text-to-speech", "jsbeaudry/haitian_creole")
# embeddings_dataset = load_dataset("Matthijs/cmu-arctic-xvectors", split="validation")
# speaker_embedding = torch.tensor(embeddings_dataset[7106]["xvector"]).unsqueeze(0)

# def generate_audio(text):

#     converted_text = replace_numbers_with_words2(text)

#     cleaned_text = cleanup_text2(converted_text)
#     final_text = normalize_text2(cleaned_text)
#     print(final_text)
#     speech = synthesiser(final_text, forward_params={"speaker_embeddings": speaker_embedding})
#     sf.write("speech.wav", speech["audio"], samplerate=speech["sampling_rate"])
#     return "speech.wav"

# # generate_audio("Kalkile koefisyan regresyon ak entèsepsyon yo lè l sèvi avèk metòd kare ki pi piti.")

# # Audio("speech.wav")

# iface = gr.Interface(
#     fn=generate_audio,
#     inputs=gr.Textbox(label="Enter text in Haitian Creole"),
#     outputs=gr.Audio(label="Generated Audio"),
#     title="Haitian Creole Text-to-Speech",
#     description="Enter text to generate Haitian Creole speech."
# )

# iface.launch()