File size: 1,845 Bytes
1956ad2 dbceb27 1956ad2 231a647 1956ad2 d393637 1956ad2 b97f697 1956ad2 b97f697 |
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 |
import torch
from transformers import pipeline
device = "cuda:0" if torch.cuda.is_available() else "cpu"
pipe = pipeline(
"automatic-speech-recognition", model="openai/whisper-base", device=device
)
from datasets import load_dataset
# dataset = load_dataset("facebook/voxpopuli", "en", split="validation", streaming=True, trust_remote_code=True)
# sample = next(iter(dataset))
def translate(audio):
outputs = pipe(audio, max_new_tokens=256, generate_kwargs={"task": "transcribe", "language": "fr"}) # "language": "fr"
return outputs["text"]
from transformers import SpeechT5Processor, SpeechT5ForTextToSpeech, SpeechT5HifiGan
processor = SpeechT5Processor.from_pretrained("microsoft/speecht5_tts")
model = SpeechT5ForTextToSpeech.from_pretrained("ccourc23/fine_tuned_SpeechT5")
vocoder = SpeechT5HifiGan.from_pretrained("microsoft/speecht5_hifigan")
embeddings_dataset = load_dataset("Matthijs/cmu-arctic-xvectors", split="validation")
speaker_embeddings = torch.tensor(embeddings_dataset[7306]["xvector"]).unsqueeze(0)
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)
synthesised_speech = synthesise(translated_text)
synthesised_speech = (synthesised_speech.numpy() * max_range).astype(np.int16)
return 16000, synthesised_speech
import gradio as gr
file_translate = gr.Interface(
fn=speech_to_speech_translation,
inputs=gr.Audio(sources="upload", type="filepath"),
outputs=gr.Audio(label="Generated Speech"),
)
file_translate.launch(share=True)
|