git clone https://github.com/THUDM/GLM-4-Voice.git
pip install matcha-tts torchaudio hyperpyyaml
cd GLM-4-Voice
# 如果出现环境问题，可以运行以下命令
pip install -r requirements.txt

import os
import uuid
from typing import List, Optional, Tuple
import torch
import torchaudio
from flow_inference import AudioDecoder
from modelscope import snapshot_download
from speech_tokenizer.modeling_whisper import WhisperVQEncoder
from speech_tokenizer.utils import extract_speech_token
from transformers import AutoModel, AutoTokenizer, GenerationConfig, WhisperFeatureExtractor
class GLM4Voice:
    def _prepare_model(self):
        model_path = snapshot_download('ZhipuAI/glm-4-voice-9b')
        decoder_path = snapshot_download('ZhipuAI/glm-4-voice-decoder')
        tokenizer_path = snapshot_download('ZhipuAI/glm-4-voice-tokenizer')
        flow_config = os.path.join(decoder_path, 'config.yaml')
        flow_checkpoint = os.path.join(decoder_path, 'flow.pt')
        hift_checkpoint = os.path.join(decoder_path, 'hift.pt')
        # GLM
        self.model = AutoModel.from_pretrained(model_path, trust_remote_code=True, device_map=self.device).eval()
        self.tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True, use_fast=False)
        # Flow & Hift
        self.audio_decoder = AudioDecoder(
            config_path=flow_config, flow_ckpt_path=flow_checkpoint, hift_ckpt_path=hift_checkpoint, device=self.device)
        # Speech tokenizer
        self.whisper_model = WhisperVQEncoder.from_pretrained(tokenizer_path).eval().to(self.device)
        self.feature_extractor = WhisperFeatureExtractor.from_pretrained(tokenizer_path)
    def clear(self):
        self.previous_tokens = ''
    def __init__(self, generation_config=None):
        if generation_config is None:
            generation_config = GenerationConfig(top_p=0.8, temperature=0.2, max_new_tokens=2000, do_sample=True)
        self.generation_config = generation_config
        self.device = 'cuda:0'
        self._prepare_model()
        self.audio_offset = self.tokenizer.convert_tokens_to_ids('<|audio_0|>')
        self.end_token_id = self.tokenizer.convert_tokens_to_ids('<|user|>')
        self.clear()
    def infer(self, audio_path: Optional[str] = None, text: Optional[str] = None) -> Tuple[str, str]:
        if audio_path is not None:
            audio_tokens = extract_speech_token(self.whisper_model, self.feature_extractor, [audio_path])[0]
            audio_tokens = ''.join([f'<|audio_{x}|>' for x in audio_tokens])
            audio_tokens = '<|begin_of_audio|>' + audio_tokens + '<|end_of_audio|>'
            user_input = audio_tokens
            system_prompt = 'User will provide you with a speech instruction. Do it step by step. First, think about the instruction and respond in a interleaved manner, with 13 text token followed by 26 audio tokens. '
        else:
            user_input = text
            system_prompt = 'User will provide you with a text instruction. Do it step by step. First, think about the instruction and respond in a interleaved manner, with 13 text token followed by 26 audio tokens.'
        text = self.previous_tokens
        text = text.strip()
        if '<|system|>' not in text:
            text += f'<|system|>\n{system_prompt}'
        text += f'<|user|>\n{user_input}<|assistant|>streaming_transcription\n'
        inputs = self.tokenizer([text], return_tensors='pt').to(self.device)
        generate_ids = self.model.generate(**inputs, generation_config=self.generation_config)[0]
        generate_ids = generate_ids[inputs['input_ids'].shape[1]:]
        self.previous_tokens += text + self.tokenizer.decode(generate_ids, spaces_between_special_tokens=False)
        return self._parse_generate_ids(generate_ids)
    def _parse_generate_ids(self, generate_ids: List[int]) -> Tuple[str, str]:
        text_tokens, audio_tokens = [], []
        this_uuid = str(uuid.uuid4())
        for token_id in generate_ids.tolist():
            if token_id >= self.audio_offset:
                audio_tokens.append(token_id - self.audio_offset)
            elif token_id != self.end_token_id:
                text_tokens.append(token_id)
        audio_tokens_pt = torch.tensor(audio_tokens, device=self.device)[None]
        tts_speech, _ = self.audio_decoder.token2wav(audio_tokens_pt, uuid=this_uuid, finalize=True)
        audio_path = f'{this_uuid}.wav'
        with open(audio_path, 'wb') as f:
            torchaudio.save(f, tts_speech.cpu(), 22050, format='wav')
        response = self.tokenizer.decode(text_tokens)
        return response, audio_path
if __name__ == '__main__':
    generation_config = GenerationConfig(top_p=0.8, temperature=0.2, max_new_tokens=2000, do_sample=True)
    glm_voice = GLM4Voice(generation_config=generation_config)
    audio_path = 'http://modelscope-open.oss-cn-hangzhou.aliyuncs.com/images/weather.wav'
    response, output_path = glm_voice.infer(audio_path=audio_path)
    print(f'response: {response}\noutput_path: {output_path}')
    text = '请用英文回答'
    response, output_path = glm_voice.infer(text=text)
    print(f'response: {response}\noutput_path: {output_path}')
    glm_voice.clear()  # 清空历史
    text = '请用英文回答'
    response, output_path = glm_voice.infer(text=text)
    print(f'response: {response}\noutput_path: {output_path}')
"""
response: 是啊，阳光明媚的，真是个出门走走的好日子！你今天有什么计划吗？
output_path: 7f146cb5-4c1f-4c2c-85d0-0a8c985c90c0.wav
response: Sure! Today's weather is really nice, isn't it? It's a great day to go out and enjoy some fresh air. Do you have any plans for today?
output_path: 9326df35-aeec-4292-856b-5c0b1688e3f8.wav
response: Sure, I'll answer in English. What would you like to know?
output_path: e6e7c94b-7532-475f-bea7-e41566a954b6.wav
"""

from PIL import Image
from transformers import AutoTokenizer, AutoModel, AutoImageProcessor, AutoModelForCausalLM
from transformers.generation.configuration_utils import GenerationConfig
from transformers.generation import LogitsProcessorList, PrefixConstrainedLogitsProcessor, UnbatchedClassifierFreeGuidanceLogitsProcessor
import torch
from modelscope import snapshot_download
# model path
EMU_HUB = snapshot_download("BAAI/Emu3-Stage1")
VQ_HUB = snapshot_download("BAAI/Emu3-VisionTokenizer")
import sys
sys.path.append(EMU_HUB)
from processing_emu3 import Emu3Processor
# prepare model and processor
model = AutoModelForCausalLM.from_pretrained(
    EMU_HUB,
    device_map="cuda:0",
    torch_dtype=torch.bfloat16,
    attn_implementation="flash_attention_2",
    trust_remote_code=True,
)
tokenizer = AutoTokenizer.from_pretrained(EMU_HUB, trust_remote_code=True, padding_side="left")
image_processor = AutoImageProcessor.from_pretrained(VQ_HUB, trust_remote_code=True)
image_tokenizer = AutoModel.from_pretrained(VQ_HUB, device_map="cuda:0", trust_remote_code=True).eval()
processor = Emu3Processor(image_processor, image_tokenizer, tokenizer, chat_template="{image_prompt}{text_prompt}")
# Image Generation
# prepare input
POSITIVE_PROMPT = " masterpiece, film grained, best quality."
NEGATIVE_PROMPT = "lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry."
classifier_free_guidance = 3.0
prompt = "a portrait of young girl."
prompt += POSITIVE_PROMPT
kwargs = dict(
    mode='G',
    ratio="1:1",
    image_area=model.config.image_area,
    return_tensors="pt",
    padding="longest",
)
pos_inputs = processor(text=prompt, **kwargs)
neg_inputs = processor(text=NEGATIVE_PROMPT, **kwargs)
# prepare hyper parameters
GENERATION_CONFIG = GenerationConfig(
    use_cache=True,
    eos_token_id=model.config.eos_token_id,
    pad_token_id=model.config.pad_token_id,
    max_new_tokens=40960,
    do_sample=True,
    top_k=2048,
)
h = pos_inputs.image_size[:, 0]
w = pos_inputs.image_size[:, 1]
constrained_fn = processor.build_prefix_constrained_fn(h, w)
logits_processor = LogitsProcessorList([
    UnbatchedClassifierFreeGuidanceLogitsProcessor(
        classifier_free_guidance,
        model,
        unconditional_ids=neg_inputs.input_ids.to("cuda:0"),
    ),
    PrefixConstrainedLogitsProcessor(
        constrained_fn ,
        num_beams=1,
    ),
])
# generate
outputs = model.generate(
    pos_inputs.input_ids.to("cuda:0"),
    GENERATION_CONFIG,
    logits_processor=logits_processor,
    attention_mask=pos_inputs.attention_mask.to("cuda:0"),
)
mm_list = processor.decode(outputs[0])
for idx, im in enumerate(mm_list):
    if not isinstance(im, Image.Image):
        continue
    im.save(f"result_{idx}.png")
# Multimodal Understanding
text = "The image depicts "
image = Image.open("assets/demo.png")
inputs = processor(
    text=text,
    image=image,
    mode='U',
    padding="longest",
    return_tensors="pt",
)
GENERATION_CONFIG = GenerationConfig(
    pad_token_id=tokenizer.pad_token_id,
    bos_token_id=tokenizer.bos_token_id,
    eos_token_id=tokenizer.eos_token_id,
    max_new_tokens=1024,
)
 outputs = model.generate(
     inputs.input_ids.to("cuda:0"),
     GENERATION_CONFIG,
     attention_mask=inputs.attention_mask.to("cuda:0"),
 )
 outputs = outputs[:, inputs.input_ids.shape[-1]:]
 answers = processor.batch_decode(outputs, skip_special_tokens=True)
 for ans in answers:
     print(ans)

!pip install diffusers -U

import torch
from diffusers import StableDiffusion3Pipeline
from modelscope import snapshot_download
model_dir = snapshot_download("AI-ModelScope/stable-diffusion-3.5-large")
pipe = StableDiffusion3Pipeline.from_pretrained(model_dir, torch_dtype=torch.bfloat16)
pipe = pipe.to("cuda")
image = pipe(
    "A capybara holding a sign that reads Hello World",
    num_inference_steps=28,
    guidance_scale=3.5,
).images[0]
image.save("capybara.png")

!git clone https://github.com/deepseek-ai/Janus.git
%cd Janus
!pip install -e .

import torch
from transformers import AutoModelForCausalLM
from janus.models import MultiModalityCausalLM, VLChatProcessor
from janus.utils.io import load_pil_images
from modelscope import snapshot_download
# specify the path to the model
model_path = snapshot_download("deepseek-ai/Janus-1.3B")
vl_chat_processor: VLChatProcessor = VLChatProcessor.from_pretrained(model_path)
tokenizer = vl_chat_processor.tokenizer
vl_gpt: MultiModalityCausalLM = AutoModelForCausalLM.from_pretrained(
    model_path, trust_remote_code=True
)
vl_gpt = vl_gpt.to(torch.bfloat16).cuda().eval()
conversation = [
    {
        "role": "User",
        "content": "<image_placeholder>\nConvert the formula into latex code.",
        "images": ["/mnt/workspace/Janus/images/equation.png"],
    },
    {"role": "Assistant", "content": ""},
]
# load images and prepare for inputs
pil_images = load_pil_images(conversation)
prepare_inputs = vl_chat_processor(
    conversations=conversation, images=pil_images, force_batchify=True
).to(vl_gpt.device)
# # run image encoder to get the image embeddings
inputs_embeds = vl_gpt.prepare_inputs_embeds(**prepare_inputs)
# # run the model to get the response
outputs = vl_gpt.language_model.generate(
    inputs_embeds=inputs_embeds,
    attention_mask=prepare_inputs.attention_mask,
    pad_token_id=tokenizer.eos_token_id,
    bos_token_id=tokenizer.bos_token_id,
    eos_token_id=tokenizer.eos_token_id,
    max_new_tokens=512,
    do_sample=False,
    use_cache=True,
)
answer = tokenizer.decode(outputs[0].cpu().tolist(), skip_special_tokens=True)
print(f"{prepare_inputs['sft_format'][0]}", answer)

import os
import PIL.Image
import torch
import numpy as np
from transformers import AutoModelForCausalLM
from janus.models import MultiModalityCausalLM, VLChatProcessor
from modelscope import snapshot_download
# specify the path to the model
model_path = snapshot_download("deepseek-ai/Janus-1.3B")
vl_chat_processor: VLChatProcessor = VLChatProcessor.from_pretrained(model_path)
tokenizer = vl_chat_processor.tokenizer
vl_gpt: MultiModalityCausalLM = AutoModelForCausalLM.from_pretrained(
    model_path, trust_remote_code=True
)
vl_gpt = vl_gpt.to(torch.bfloat16).cuda().eval()
conversation = [
    {
        "role": "User",
        "content": "A stunning princess from kabul in red, white traditional clothing, blue eyes, brown hair",
    },
    {"role": "Assistant", "content": ""},
]
sft_format = vl_chat_processor.apply_sft_template_for_multi_turn_prompts(
    conversations=conversation,
    sft_format=vl_chat_processor.sft_format,
    system_prompt="",
)
prompt = sft_format + vl_chat_processor.image_start_tag
@torch.inference_mode()
def generate(
    mmgpt: MultiModalityCausalLM,
    vl_chat_processor: VLChatProcessor,
    prompt: str,
    temperature: float = 1,
    parallel_size: int = 16,
    cfg_weight: float = 5,
    image_token_num_per_image: int = 576,
    img_size: int = 384,
    patch_size: int = 16,
):
    input_ids = vl_chat_processor.tokenizer.encode(prompt)
    input_ids = torch.LongTensor(input_ids)
    tokens = torch.zeros((parallel_size*2, len(input_ids)), dtype=torch.int).cuda()
    for i in range(parallel_size*2):
        tokens[i, :] = input_ids
        if i % 2 != 0:
            tokens[i, 1:-1] = vl_chat_processor.pad_id
    inputs_embeds = mmgpt.language_model.get_input_embeddings()(tokens)
    generated_tokens = torch.zeros((parallel_size, image_token_num_per_image), dtype=torch.int).cuda()
    for i in range(image_token_num_per_image):
        outputs = mmgpt.language_model.model(inputs_embeds=inputs_embeds, use_cache=True, past_key_values=outputs.past_key_values if i != 0 else None)
        hidden_states = outputs.last_hidden_state
        logits = mmgpt.gen_head(hidden_states[:, -1, :])
        logit_cond = logits[0::2, :]
        logit_uncond = logits[1::2, :]
        logits = logit_uncond + cfg_weight * (logit_cond-logit_uncond)
        probs = torch.softmax(logits / temperature, dim=-1)
        next_token = torch.multinomial(probs, num_samples=1)
        generated_tokens[:, i] = next_token.squeeze(dim=-1)
        next_token = torch.cat([next_token.unsqueeze(dim=1), next_token.unsqueeze(dim=1)], dim=1).view(-1)
        img_embeds = mmgpt.prepare_gen_img_embeds(next_token)
        inputs_embeds = img_embeds.unsqueeze(dim=1)
    dec = mmgpt.gen_vision_model.decode_code(generated_tokens.to(dtype=torch.int), shape=[parallel_size, 8, img_size//patch_size, img_size//patch_size])
    dec = dec.to(torch.float32).cpu().numpy().transpose(0, 2, 3, 1)
    dec = np.clip((dec + 1) / 2 * 255, 0, 255)
    visual_img = np.zeros((parallel_size, img_size, img_size, 3), dtype=np.uint8)
    visual_img[:, :, :] = dec
    os.makedirs('generated_samples', exist_ok=True)
    for i in range(parallel_size):
        save_path = os.path.join('generated_samples', "img_{}.jpg".format(i))
        PIL.Image.fromarray(visual_img[i]).save(save_path)
generate(
    vl_gpt,
    vl_chat_processor,
    prompt,
)