pip install -r requirements.txt

from transformers import AutoModelForCausalLM, AutoTokenizer
from transformers.generation import GenerationConfig
import torch
torch.manual_seed(1234)

# 请注意：分词器默认行为已更改为默认关闭特殊token攻击防护。
tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen-Audio-Chat", trust_remote_code=True)

# 打开bf16精度，A100、H100、RTX3060、RTX3070等显卡建议启用以节省显存
# model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen-Audio-Chat", device_map="auto", trust_remote_code=True, bf16=True).eval()
# 打开fp16精度，V100、P100、T4等显卡建议启用以节省显存
# model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen-Audio-Chat", device_map="auto", trust_remote_code=True, fp16=True).eval()
# 使用CPU进行推理，需要约32GB内存
# model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen-Audio-Chat", device_map="cpu", trust_remote_code=True).eval()
# 默认gpu进行推理，需要约24GB显存
model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen-Audio-Chat", device_map="cuda", trust_remote_code=True).eval()

# 可指定不同的生成长度、top_p等相关超参（transformers 4.32.0及以上无需执行此操作）
# model.generation_config = GenerationConfig.from_pretrained("Qwen/Qwen-Audio-Chat", trust_remote_code=True)

# 第一轮对话
query = tokenizer.from_list_format([
    {'audio': 'assets/audio/1272-128104-0000.flac'}, # Either a local path or an url
    {'text': 'what does the person say?'},
])
response, history = model.chat(tokenizer, query=query, history=None)
print(response)
# The person says: "mister quilter is the apostle of the middle classes and we are glad to welcome his gospel".

# 第二轮对话
response, history = model.chat(tokenizer, 'Find the start time and end time of the word "middle classes"', history=history)
print(response)
# The word "middle classes" starts at <|2.33|> seconds and ends at <|3.26|> seconds.

from transformers import AutoModelForCausalLM, AutoTokenizer
from transformers.generation import GenerationConfig
import torch
torch.manual_seed(1234)

tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen-Audio", trust_remote_code=True)

# 打开bf16精度，A100、H100、RTX3060、RTX3070等显卡建议启用以节省显存
# model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen-Audio", device_map="auto", trust_remote_code=True, bf16=True).eval()
# 打开fp16精度，V100、P100、T4等显卡建议启用以节省显存
# model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen-Audio", device_map="auto", trust_remote_code=True, fp16=True).eval()
# 使用CPU进行推理，需要约32GB内存
# model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen-Audio", device_map="cpu", trust_remote_code=True).eval()
# 默认gpu进行推理，需要约24GB显存
model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen-Audio", device_map="cuda", trust_remote_code=True).eval()

# 可指定不同的生成长度、top_p等相关超参（transformers 4.32.0及以上无需执行此操作）
# model.generation_config = GenerationConfig.from_pretrained("Qwen/Qwen-Audio", trust_remote_code=True)
audio_url = "assets/audio/1272-128104-0000.flac"
sp_prompt = "<|startoftranscription|><|en|><|transcribe|><|en|><|notimestamps|><|wo_itn|>"
query = f"<audio>{audio_url}</audio>{sp_prompt}"
audio_info = tokenizer.process_audio(query)
inputs = tokenizer(query, return_tensors='pt', audio_info=audio_info)
inputs = inputs.to(model.device)
pred = model.generate(**inputs, audio_info=audio_info)
response = tokenizer.decode(pred.cpu()[0], skip_special_tokens=False,audio_info=audio_info)
print(response)
# <audio>assets/audio/1272-128104-0000.flac</audio><|startoftranscription|><|en|><|transcribe|><|en|><|notimestamps|><|wo_itn|>mister quilting is the apostle of the middle classes and we are glad to welcome his gospel<|endoftext|>
# 

from modelscope import snapshot_download
from transformers import AutoModelForCausalLM, AutoTokenizer

# Downloading model checkpoint to a local dir model_dir
model_id = 'qwen/Qwen-Audio-Chat'
revision = 'master'
model_dir = snapshot_download(model_id, revision=revision)

# Loading local checkpoints
# trust_remote_code is still set as True since we still load codes from local dir instead of transformers
tokenizer = AutoTokenizer.from_pretrained(model_dir, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
    model_dir,
    device_map="cuda",
    trust_remote_code=True
).eval()

from modelscope import (
    snapshot_download, AutoModelForCausalLM, AutoTokenizer, GenerationConfig
)
import torch
model_id = 'qwen/Qwen-Audio-Chat'
revision = 'master'

model_dir = snapshot_download(model_id, revision=revision)
torch.manual_seed(1234)

tokenizer = AutoTokenizer.from_pretrained(model_dir, trust_remote_code=True)
if not hasattr(tokenizer, 'model_dir'):
    tokenizer.model_dir = model_dir
# 打开bf16精度，A100、H100、RTX3060、RTX3070等显卡建议启用以节省显存
# model = AutoModelForCausalLM.from_pretrained(model_dir, device_map="auto", trust_remote_code=True, bf16=True).eval()
# 打开fp16精度，V100、P100、T4等显卡建议启用以节省显存
# model = AutoModelForCausalLM.from_pretrained(model_dir, device_map="auto", trust_remote_code=True, fp16=True).eval()
# 使用CPU进行推理，需要约32GB内存
# model = AutoModelForCausalLM.from_pretrained(model_dir, device_map="cpu", trust_remote_code=True).eval()
# 默认gpu进行推理，需要约24GB显存
model = AutoModelForCausalLM.from_pretrained(model_dir, device_map="auto", trust_remote_code=True).eval()

# 第一轮对话
query = tokenizer.from_list_format([
    {'audio': 'assets/audio/1272-128104-0000.flac'}, # Either a local path or an url
    {'text': 'what does the person say?'},
])
response, history = model.chat(tokenizer, query=query, history=None)
print(response)
# The person says: "mister quilter is the apostle of the middle classes and we are glad to welcome his gospel".

# 第二轮对话
response, history = model.chat(tokenizer, 'Find the start time and end time of the word "middle classes"', history=history)
print(response)
# The word "middle classes" starts at <|2.33|> seconds and ends at <|3.26|> seconds.

pip install -r requirements_web_demo.txt

python web_demo_audio.py

@article{Qwen-Audio,
  title={Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models},
  author={Chu, Yunfei and Xu, Jin and Zhou, Xiaohuan and Yang, Qian and Zhang, Shiliang and Yan, Zhijie  and Zhou, Chang and Zhou, Jingren},
  journal={arXiv preprint arXiv:2311.07919},
  year={2023}
}