app2.py

from transformers import pipeline
import torch
from IPython.display import Audio

device = "cuda:0" if torch.cuda.is_available() else "cpu"

classifier = pipeline(
    "audio-classification", model="MIT/ast-finetuned-speech-commands-v2", device=device
)

from transformers.pipelines.audio_utils import ffmpeg_microphone_live

print(classifier.model.config.id2label)

def launch_fn(
    wake_word="marvin",
    prob_threshold=0.5,
    chunk_length_s=2.0,
    stream_chunk_s=0.25,
    debug=False,
):
    if wake_word not in classifier.model.config.label2id.keys():
        raise ValueError(
            f"Wake word {wake_word} not in set of valid class labels, pick a wake word in the set {classifier.model.config.label2id.keys()}."
        )

    sampling_rate = classifier.feature_extractor.sampling_rate

    mic = ffmpeg_microphone_live(
        sampling_rate=sampling_rate,
        chunk_length_s=chunk_length_s,
        stream_chunk_s=stream_chunk_s,
    )

    print("Listening for wake word...")
    for prediction in classifier(mic):
        prediction = prediction[0]
        if debug:
            print(prediction)
        if prediction["label"] == wake_word:
            if prediction["score"] > prob_threshold:
                return True
            
# launch_fn(debug=True)

transcriber = pipeline(
    "automatic-speech-recognition", model="openai/whisper-base.en", device=device
)

import sys


def transcribe(chunk_length_s=5.0, stream_chunk_s=1.0):
    sampling_rate = transcriber.feature_extractor.sampling_rate

    mic = ffmpeg_microphone_live(
        sampling_rate=sampling_rate,
        chunk_length_s=chunk_length_s,
        stream_chunk_s=stream_chunk_s,
    )

    print("Start speaking...")
    for item in transcriber(mic, generate_kwargs={"max_new_tokens": 128}):
        sys.stdout.write("\033[K")
        print(item["text"], end="\r")
        if not item["partial"][0]:
            break

    return item["text"]

from huggingface_hub import HfFolder
import requests


def query(text, model_id="tiiuae/falcon-7b-instruct"):
    api_url = f"https://api-inference.huggingface.co/models/{model_id}"
    headers = {"Authorization": f"Bearer {HfFolder().get_token()}"}
    payload = {"inputs": text}

    print(f"Querying...: {text}")
    response = requests.post(api_url, headers=headers, json=payload)
    return response.json()[0]["generated_text"][len(text) + 1 :]

from transformers import SpeechT5Processor, SpeechT5ForTextToSpeech, SpeechT5HifiGan

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)

from datasets import load_dataset

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()


# launch_fn()
# print("hablá")
# transcription = transcribe()
# response = query(transcription)
# audio = synthesise(response)


audio = synthesise(
    "Hugging Face is a company that provides natural language processing and machine learning tools for developers."
)





# import gradio as gr

# with gr.Blocks() as demo:
#     boton = gr.Button("hablar")
#     audio = gr.Audio()
#     micro = gr.Microphone()
#     boton.click(start,micro,audio)