CiSiMi v0.1

Explain to me how gravity works!

pip install outetts llama-cpp-python --upgrade
pip install huggingface_hub sounddevice

import torch
import outetts
import numpy as np
from huggingface_hub import hf_hub_download
from outetts.wav_tokenizer.audio_codec import AudioCodec
from outetts.version.v2.prompt_processor import PromptProcessor
from outetts.version.playback import ModelOutput

# Download the model
model_path = hf_hub_download(
    repo_id="KandirResearch/CiSiMi-v0.1",
    filename="unsloth.Q8_0.gguf",
)

# Configure the model
model_config = outetts.GGUFModelConfig_v2(
    model_path=model_path,
    tokenizer_path="KandirResearch/CiSiMi-v0.1",
)

# Initialize components
interface = outetts.InterfaceGGUF(model_version="0.3", cfg=model_config)
audio_codec = AudioCodec()
prompt_processor = PromptProcessor("KandirResearch/CiSiMi-v0.1")

device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
gguf_model = interface.get_model()

# Helper function to extract audio from tokens
def get_audio(tokens):
    outputs = prompt_processor.extract_audio_from_tokens(tokens)
    if not outputs:
        return None
    audio_tensor = audio_codec.decode(torch.tensor([[outputs]], dtype=torch.int64).to(device))
    return ModelOutput(audio_tensor, audio_codec.sr)

# Helper function to clean text output
def extract_text_from_tts_output(tts_output):
    text = ""
    for line in tts_output.strip().split('\n'):
        if '<|audio_end|>' in line or '<|im_end|>' in line:
            continue
        if '<|' in line:
            word = line.split('<|')[0].strip()
            if word:
                text += word + " "
        else:
            text += line.strip() + " "
    return text.strip()

# Generate response function
def generate_response(instruction):
    prompt = f"<|im_start|>\nInstructions:\n{instruction}\n<|im_end|>\nAnswer:\n"
    gen_cfg = outetts.GenerationConfig(
        text=prompt, 
        temperature=0.6, 
        repetition_penalty=1.1, 
        max_length=4096, 
        speaker=None
    )
    
    input_ids = prompt_processor.tokenizer.encode(prompt)
    tokens = gguf_model.generate(input_ids, gen_cfg)
    
    output_text = prompt_processor.tokenizer.decode(tokens, skip_special_tokens=False)
    
    if "<|audio_end|>" in output_text:
        first_part, _, _ = output_text.partition("<|audio_end|>")
        
        if "<|audio_end|>\n<|im_end|>\n" not in first_part:
            first_part += "<|audio_end|>\n<|im_end|>\n"
            
        extracted_text = extract_text_from_tts_output(first_part)
        
        audio_start_pos = first_part.find("<|audio_start|>\n") + len("<|audio_start|>\n")
        audio_end_pos = first_part.find("<|audio_end|>\n<|im_end|>\n") + len("<|audio_end|>\n<|im_end|>\n")
        
        if audio_start_pos >= len("<|audio_start|>\n") and audio_end_pos > audio_start_pos:
            audio_tokens_text = first_part[audio_start_pos:audio_end_pos]
            audio_tokens = prompt_processor.tokenizer.encode(audio_tokens_text)
            audio_output = get_audio(audio_tokens)
            
            if audio_output is not None and hasattr(audio_output, 'audio') and audio_output.audio is not None:
                audio_numpy = audio_output.audio.cpu().numpy()
                if audio_numpy.ndim > 1:
                    audio_numpy = audio_numpy.squeeze()
                
                return extracted_text, (audio_output.sr, audio_numpy)
    
    return output_text, None

# Example usage
question = "What is the meaning of life?"
response_text, response_audio = generate_response(question)
print(response_text)

# Play audio if available
if response_audio is not None:
    if "ipykernel" in sys.modules:
        from IPython.display import display, Audio
        display(Audio(response_audio[1], rate=response_audio[0], autoplay=True))
    else:
        import sounddevice as sd
        sd.play(response_audio[1], samplerate=response_audio[0])
        sd.wait()