text_to_audio.py

from io import BytesIO
from urllib.request import urlopen
import librosa
from transformers import Qwen2AudioForConditionalGeneration, AutoProcessor, pipeline
import pyttsx3  # For text-to-speech

# Load Qwen2Audio model and processor
processor = AutoProcessor.from_pretrained("Qwen/Qwen2-Audio-7B-Instruct")
model = Qwen2AudioForConditionalGeneration.from_pretrained("Qwen/Qwen2-Audio-7B-Instruct", device_map="auto")

# Initialize TTS engine
tts_engine = pyttsx3.init()

# Sample conversation with audio input
conversation = [
    {"role": "user", "content": [
        {"type": "audio", "audio_url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen2-Audio/audio/guess_age_gender.wav"},
    ]},
    {"role": "assistant", "content": "Yes, the speaker is female and in her twenties."},
    {"role": "user", "content": [
        {"type": "audio", "audio_url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen2-Audio/audio/translate_to_chinese.wav"},
    ]},
]

# Preprocess conversation
text = processor.apply_chat_template(conversation, add_generation_prompt=True, tokenize=False)
audios = []
for message in conversation:
    if isinstance(message["content"], list):
        for ele in message["content"]:
            if ele["type"] == "audio":
                audios.append(librosa.load(
                    BytesIO(urlopen(ele['audio_url']).read()),
                    sr=processor.feature_extractor.sampling_rate)[0]
                )

# Prepare model inputs
inputs = processor(text=text, audios=audios, return_tensors="pt", padding=True)
inputs.input_ids = inputs.input_ids.to("cuda")

# Generate response
generate_ids = model.generate(**inputs, max_length=256)
generate_ids = generate_ids[:, inputs.input_ids.size(1):]

# Decode response
response = processor.batch_decode(generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0]
print("Model Response:", response)

# Convert response to speech
tts_engine.say(response)
tts_engine.runAndWait()