app.py

import torch
from transformers import pipeline
from datasets import load_dataset
from datasets import Audio
from transformers import SpeechT5Processor, SpeechT5ForTextToSpeech, SpeechT5HifiGan


device = "cuda:0" if torch.cuda.is_available() else "cpu"
pipe = pipeline(
    "automatic-speech-recognition", model="openai/whisper-base", device=device
)

processor = SpeechT5Processor.from_pretrained("microsoft/speecht5_tts")

model = SpeechT5ForTextToSpeech.from_pretrained("microsoft/speecht5_tts").to(device)
vocoder = SpeechT5HifiGan.from_pretrained("microsoft/speecht5_hifigan").to(device)


embeddings_dataset = load_dataset("Matthijs/cmu-arctic-xvectors", split="validation")
speaker_embeddings = torch.tensor(embeddings_dataset[7306]["xvector"]).unsqueeze(0)

def translate(audio):
    outputs = pipe(audio, max_new_tokens=256, generate_kwargs={"task": "translate","language": "fr"})
    return outputs["text"]

def synthesise(text):
    inputs = processor(text=text, return_tensors="pt")
    speech = model.generate_speech(
        inputs["input_ids"].to(device), speaker_embeddings.to(device), vocoder=vocoder
    )
    return speech.cpu()

import numpy as np

target_dtype = np.int16
max_range = np.iinfo(target_dtype).max


def speech_to_speech_translation(audio):
    translated_text = translate(audio)
    print(f"{translated_text}")
    synthesised_speech = synthesise(translated_text)
    synthesised_speech = (synthesised_speech.numpy() * max_range).astype(np.int16)
    return 16000, synthesised_speech

import gradio as gr

demo = gr.Blocks()

mic_translate = gr.Interface(
    fn=speech_to_speech_translation,
    inputs=gr.Audio(sources= ["microphone","upload"], type="filepath"),
    outputs=gr.Audio(label="Generated Speech", type="numpy"),
)

file_translate = gr.Interface(
    fn=speech_to_speech_translation,
    inputs=gr.Audio(sources=["upload"], type="filepath"),
    outputs=gr.Audio(label="Generated Speech", type="numpy"),
)

with demo:
    gr.TabbedInterface([mic_translate, file_translate], ["Microphone", "Audio File"])

demo.launch()