File size: 16,317 Bytes
45cf443 92c7321 45cf443 cecc5b1 45cf443 cecc5b1 45cf443 cecc5b1 45cf443 cecc5b1 45cf443 cecc5b1 45cf443 cecc5b1 45cf443 cecc5b1 45cf443 cecc5b1 45cf443 c6bc767 45cf443 c6bc767 45cf443 | 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 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 | import argparse
import os
import random
import time
import warnings
import torch
from PIL import Image
from transformers import AutoTokenizer, AutoModelForCausalLM
from models import VAM, VAMConfig
from dataset import VAMDataset
from utils import setup_seed, log_model_params
warnings.filterwarnings('ignore')
def init_model(args):
ckpt_dir = args.load_from
# check for checkpoint/omni-o/omni-o.pth style paths
weight_name = args.weight
if not weight_name.endswith('.pth'):
if args.use_moe and not weight_name.endswith('_moe'):
weight_name = f'{weight_name}_moe.pth'
else:
weight_name = f'{weight_name}.pth'
ckp = os.path.join(ckpt_dir, weight_name)
config = VAMConfig(
hidden_size=args.hidden_size,
num_hidden_layers=args.num_hidden_layers,
num_attention_heads=args.hidden_size // 96,
num_key_value_heads=args.hidden_size // 192,
use_moe=bool(args.use_moe)
)
model = VAM(config, audio_encoder_path=args.sensevoice_dir, vision_model_path=args.siglip_dir)
state = torch.load(ckp, map_location=args.device, weights_only=True)
missing, unexpected = model.load_state_dict(state, strict=False)
if missing:
print(f' Missing keys (expected for encoders): {len(missing)}')
if unexpected:
print(f' Unexpected keys: {len(unexpected)}')
log_model_params(model)
if model.audio_encoder is not None and hasattr(model.audio_encoder, 'to'):
model.audio_encoder.to(args.device)
if model.vision_encoder is not None and hasattr(model.vision_encoder, 'to'):
model.vision_encoder.to(args.device)
from transformers import MimiModel
model.mimi_model = MimiModel.from_pretrained(args.mimi_dir).eval()
tokenizer = AutoTokenizer.from_pretrained(args.tokenizer_dir)
return model.half().eval().to(args.device), tokenizer
def eval_sample(model, tokenizer, args, idx, prompt, audio_inputs, output_name, pixel_values=None, history=None, audio_lens=None, ref_codes=None, spk_emb=None):
import soundfile as sf
try:
from pydub import AudioSegment
except ImportError:
AudioSegment = None
messages = (history or []) + [{"role": "user", "content": prompt}]
inputs_text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
x = torch.tensor(tokenizer(inputs_text)['input_ids'], dtype=torch.long, device=args.device)[None, ...]
audio_frames = []
with torch.no_grad():
res_y = model.generate(x, tokenizer.eos_token_id, max_new_tokens=args.max_new_tokens,
temperature=args.temperature, top_p=args.top_p, stream=True,
return_audio_codes=True,
audio_inputs=audio_inputs, audio_lens=audio_lens, pixel_values=pixel_values,
ref_codes=ref_codes, spk_emb=spk_emb)
print('📒 [Thinker]: ', end='', flush=True)
history_idx = 0
for y, audio_frame in res_y:
if y is not None:
answer = tokenizer.decode(y[0].tolist(), skip_special_tokens=True)
if answer and answer[-1] != '�':
print(answer[history_idx:], end='', flush=True)
history_idx = len(answer)
if audio_frame:
audio_frames.append(audio_frame)
print()
if audio_frames:
print(f'🎹 [Talker]: {len(audio_frames)} frames', end=" ")
if args.decode_audio:
try:
codes = [f for f in audio_frames if f and len(f) == 8]
if not codes:
print('⚠️ 生成的Mimi codes为空，跳过保存。')
return
mimi_codes = torch.tensor(codes, dtype=torch.long).T.unsqueeze(0).to(args.device)
filtered = torch.where(mimi_codes >= 2049, torch.zeros_like(mimi_codes), mimi_codes)
audio = model.mimi_model.decode(filtered).audio_values
output_path = os.path.join(args.output_dir, output_name)
wav_path = output_path.rsplit('.', 1)[0] + '.wav'
sf.write(wav_path, audio.squeeze().float().cpu().numpy(), 24000)
if AudioSegment is not None:
AudioSegment.from_wav(wav_path).export(output_path, format='mp3', bitrate='64k')
os.remove(wav_path)
else:
print(f'pydub not installed, keeping .wav: {wav_path}')
print(f'| Audio decoded to: {output_path}')
except Exception as e:
print(f'⚠️ 保存音频失败: {str(e)}')
else:
print("(decode_audio=off)\n")
def main():
parser = argparse.ArgumentParser(description="Omni-O Chat")
parser.add_argument('--load_from', default='checkpoint/omni-o', type=str, help="模型权重目录（包含omni-o.pth）")
parser.add_argument('--weight', default='omni-o', type=str, help="权重文件名（不含.pth后缀）")
parser.add_argument('--tokenizer_dir', default='checkpoint/omni/native_hf', type=str, help="tokenizer目录")
parser.add_argument('--sensevoice_dir', default='checkpoint/sensevoice', type=str, help="SenseVoice目录")
parser.add_argument('--siglip_dir', default='checkpoint/siglip', type=str, help="SigLIP目录")
parser.add_argument('--mimi_dir', default='checkpoint/mimi', type=str, help="Mimi目录")
parser.add_argument('--hidden_size', default=768, type=int, help="隐藏层维度")
parser.add_argument('--num_hidden_layers', default=8, type=int, help="隐藏层数量")
parser.add_argument('--use_moe', default=0, type=int, choices=[0, 1], help="是否使用MoE架构")
parser.add_argument('--max_new_tokens', default=512, type=int, help="最大生成长度")
parser.add_argument('--temperature', default=0.7, type=float, help="Thinker生成温度")
parser.add_argument('--top_p', default=0.85, type=float, help="nucleus采样阈值")
parser.add_argument('--output_dir', default='./output_audio/', type=str, help="输出音频保存目录")
parser.add_argument('--device', default='cuda' if torch.cuda.is_available() else 'cpu', type=str, help="运行设备")
parser.add_argument('--audio_dir', default='./dataset/eval_omni/', type=str, help="测试音频目录")
parser.add_argument('--image_dir', default='./dataset/eval_omni/', type=str, help="测试图像目录")
parser.add_argument('--open_thinking', default=0, type=int, help="是否开启思考模式（0=否，1=是）（思考模式下禁用audio输出）")
parser.add_argument('--decode_audio', default=1, type=int, help="是否解码音频输出（0=否，1=是）")
parser.add_argument('--mode', default='0', type=str, help="评估模式：-1=all 0=text 1=multi 2=audio 3=clone 4=image 5=mix（逗号组合，如 2,5）")
parser.add_argument('--prompt_lang', default=0, type=int, choices=[0, 1, 2], help="问题语言：0=英文 1=中文 2=英文+中文")
args = parser.parse_args()
modes = set(args.mode.replace(',', '').replace('-1', '012345'))
os.makedirs(args.output_dir, exist_ok=True)
model, tokenizer = init_model(args)
setup_seed(int(time.time()) % 31415926)
if '0' in modes:
print('\n\n==================== text -> {text, audio} ====================')
test_prompts_en = [
"Tell me an interesting fact about space.", "How do I make a cup of coffee?", "What's the weather like today?",
"Will it rain tomorrow?", "Tell me a joke.", "Can you sing a song for me?", "Please introduce yourself."
]
test_prompts_zh = [
"告诉我一个关于太空的有趣事实。", "如何制作一杯咖啡？", "今天的天气怎么样？",
"明天会下雨吗？", "给我讲个笑话吧", "你能为我唱首歌吗？", "介绍一下你自己"
]
test_prompts = [test_prompts_en, test_prompts_zh, test_prompts_en + test_prompts_zh][args.prompt_lang]
for idx, prompt in enumerate(test_prompts):
print(f'\n📝 [text-{idx+1}]: {prompt}')
eval_sample(model, tokenizer, args, idx, prompt, None, f"text-{idx:02d}.mp3")
if '1' in modes:
print('\n\n==================== multi-turn -> {text, audio} ====================')
multi_turn_tests_zh = [
{
"history": [
{"role": "user", "content": "你好"},
{"role": "assistant", "content": "你好！有什么可以帮你的吗？"}
],
"prompt": "我想找点事做，你有什么建议吗？"
},
{
"history": [
{"role": "user", "content": "你好"},
{"role": "assistant", "content": "你好！有什么可以帮你的吗？"},
{"role": "user", "content": "我想找点事做，你有什么建议吗？"},
{"role": "assistant", "content": "可以听听音乐或者看看书，放松一下心情。"}
],
"prompt": "好的，那我去照做了，谢谢你"
}
]
multi_turn_tests_en = [
{
"history": [
{"role": "user", "content": "Hello"},
{"role": "assistant", "content": "Hello! How can I help you?"}
],
"prompt": "I want to find something to do. Do you have any suggestions?"
},
{
"history": [
{"role": "user", "content": "Hello"},
{"role": "assistant", "content": "Hello! How can I help you?"},
{"role": "user", "content": "I want to find something to do. Do you have any suggestions?"},
{"role": "assistant", "content": "You can listen to music or read a book to relax a little."}
],
"prompt": "Okay, I will try that. Thank you."
}
]
multi_turn_tests = [multi_turn_tests_en, multi_turn_tests_zh, multi_turn_tests_en + multi_turn_tests_zh][args.prompt_lang]
for idx, test in enumerate(multi_turn_tests):
print(f'\n💬 [multi-{idx+1}]')
for msg in test["history"]: print(f' {msg["role"]}: {msg["content"]}')
print(f' user: {test["prompt"]}')
eval_sample(model, tokenizer, args, idx, test["prompt"], None, f"multi-{idx:02d}.mp3", history=test["history"])
if '2' in modes:
print('\n\n==================== audio -> {text, audio} ====================')
audio_files_en = sorted([f for f in os.listdir(args.audio_dir) if f.startswith('audio-en-') and f.lower().endswith(('.mp3', '.wav'))])
audio_files_zh = sorted([f for f in os.listdir(args.audio_dir) if f.startswith('audio-zh-') and f.lower().endswith(('.mp3', '.wav'))])
audio_files = [audio_files_en, audio_files_zh, audio_files_en + audio_files_zh][args.prompt_lang]
for idx, audio_file in enumerate(audio_files):
print(f'\n🎤 [audio-{idx+1}]: {audio_file}')
mel, valid_len = VAMDataset.process_audio(os.path.join(args.audio_dir, audio_file), model.audio_processor)
audio_inputs = mel.unsqueeze(0).to(args.device)
audio_lens = torch.tensor([valid_len], device=args.device)
audio_token_len = valid_len or 1
prompt = model.config.audio_special_token * audio_token_len
eval_sample(model, tokenizer, args, idx, prompt, audio_inputs, f"audio-{idx:02d}-{os.path.splitext(audio_file)[0]}.mp3", audio_lens=audio_lens)
if '3' in modes:
print('\n\n==================== clone voice -> {text, audio} ====================')
clone_prompts_en = ["Hello, please introduce yourself.", "What's the weather like today?", "Tell me a joke."]
clone_prompts_zh = ["你好，请介绍一下你自己。", "今天天气怎么样？", "给我讲个笑话吧"]
clone_prompts = [clone_prompts_en, clone_prompts_zh, clone_prompts_en + clone_prompts_zh][args.prompt_lang]
voices_pt = os.path.join(os.path.dirname(os.path.abspath(__file__)), 'model', 'speaker', 'voices_unseen.pt')
voices = [('default', None, None)]
if os.path.exists(voices_pt):
voice_data = torch.load(voices_pt, map_location=args.device)
for speaker, v in sorted(voice_data.items()):
rc = v['ref_codes'].unsqueeze(0).to(args.device)
se = v['spk_emb'].half().unsqueeze(0).to(args.device) if 'spk_emb' in v else None
voices.append((speaker, rc, se))
for speaker, rc, se in voices:
info = f'ref_codes: {rc.shape[2]} frames, spk_emb: {"+" if se is not None else "-"}' if rc is not None else ('spk_emb only' if se is not None else 'default')
print(f'\n🎵 [clone: {speaker}] {info}')
for idx, prompt in enumerate(clone_prompts):
print(f' 📝 [text-{idx+1}]: {prompt}')
history = [{"role": "system", "content": "你是一个专业的语音助手，请用给定的音色风格来回答用户的问题。请尽量详细地回答，给出有价值的信息。"}]
eval_sample(model, tokenizer, args, idx, prompt, None, f"clone-{speaker}-{idx:02d}.mp3", ref_codes=rc, history=history, spk_emb=se)
if '4' in modes:
print('\n\n==================== image -> {text, audio} ====================')
image_files = sorted([f for f in os.listdir(args.image_dir) if f.lower().endswith(('.jpg', '.jpeg', '.png'))])
for idx, image_file in enumerate(image_files):
print(f'\n🖼️ [image-{idx+1}]: {image_file}')
image = Image.open(os.path.join(args.image_dir, image_file)).convert('RGB')
pixel_values = {k: v.to(args.device) for k, v in model.vision_processor(images=image, return_tensors="pt").items()}
prompts = [["Please describe this image."], ["请描述这张图片"], ["Please describe this image.", "请描述这张图片"]][args.prompt_lang]
for lang_idx, prompt_text in enumerate(prompts):
prompt = prompt_text + "\n\n" + model.config.image_special_token * model.config.image_token_len
eval_sample(model, tokenizer, args, idx, prompt, None, f"image-{idx:02d}-{lang_idx}-{os.path.splitext(image_file)[0]}.mp3", pixel_values=pixel_values)
if '5' in modes:
print('\n\n==================== text+audio+image -> {text, audio} ====================')
img_audio_files = sorted([f for f in os.listdir(args.audio_dir) if f.startswith('img-') and f.lower().endswith(('.mp3', '.wav'))])
image_files = sorted([f for f in os.listdir(args.image_dir) if f.lower().endswith(('.jpg', '.jpeg', '.png'))])
text_hints = [["Please answer me: "], ["请回答我："], ["Please answer me: ", "请回答我："]][args.prompt_lang]
for idx, image_file in enumerate(image_files):
audio_file = random.choice(img_audio_files)
image = Image.open(os.path.join(args.image_dir, image_file)).convert('RGB')
pixel_values = {k: v.to(args.device) for k, v in model.vision_processor(images=image, return_tensors="pt").items()}
for lang_idx, text_hint in enumerate(text_hints):
print(f'\n🌀 [mix-{idx+1}-{lang_idx}]: {text_hint} | {audio_file} | {image_file}')
mel, valid_len = VAMDataset.process_audio(os.path.join(args.audio_dir, audio_file), model.audio_processor)
audio_inputs = mel.unsqueeze(0).to(args.device)
audio_lens = torch.tensor([valid_len], device=args.device)
audio_token_len = valid_len or 1
prompt = text_hint + model.config.audio_special_token * audio_token_len + "\n\n" + model.config.image_special_token * model.config.image_token_len
eval_sample(model, tokenizer, args, idx, prompt, audio_inputs, f"mix-{idx:02d}-{lang_idx}-{os.path.splitext(image_file)[0]}.mp3", pixel_values=pixel_values, audio_lens=audio_lens)
if __name__ == "__main__":
main()
|