[中文](README_CN.md)  ｜   English  
Qwen2-Audio-7B 🤖 | 🤗  ｜ Qwen-Audio-7B-Instruct 🤖| 🤗  ｜ Demo🤖 | 🤗 
📑 Paper    |    📑 Blog    |    💬 WeChat (微信)   |    Discord  
We introduce the latest progress of Qwen-Audio, a large-scale audio-language model called Qwen2-Audio, which is capable of accepting various audio signal inputs and performing audio analysis or direct textual responses with regard to speech instructions. We introduce two distinct audio interaction modes:
- voice chat: users can freely engage in voice interactions with Qwen2-Audio without text input;
- audio analysis: users could provide audio and text instructions for analysis during the interaction;
We've released two models of the Qwen2-Audio series: Qwen2-Audio-7B and Qwen2-Audio-7B-Instruct.
Architecture
The overview of three-stage training process of Qwen2-Audio.
News and Updates
- 2024.8.9 🎉 We released the checkpoints of both
Qwen2-Audio-7BandQwen2-Audio-7B-Instructon ModelScope and Hugging Face. - 2024.7.15 🎉 We released the paper of Qwen2-Audio, introducing the relevant model structure, training methods, and model performance. Check our report for details!
- 2023.11.30 🔥 We released the Qwen-Audio series.
Evaluation
We evaluated the Qwen2-Audio's abilities on 13 standard benchmarks as follows:
Task
Description
Dataset
Split
Metric
ASR
Automatic Speech Recognition
Fleurs
dev | test
WER
Aishell2
test
Librispeech
dev | test
Common Voice
dev | test
S2TT
Speech-to-Text Translation
CoVoST2
test
BLEU
SER
Speech Emotion Recognition
Meld
test
ACC
VSC
Vocal Sound Classification
VocalSound
test
ACC
Chat-Benchmark-Speech
Fisher
SpokenWOZ
IEMOCAP
Common voice
dev | test
GPT-4 Eval
Chat-Benchmark-Sound
Clotho
dev | test
GPT-4 Eval
Chat-Benchmark-Music
MusicCaps
dev | test
GPT-4 Eval
Chat-Benchmark-Mixed-Audio
Common voice
AudioCaps
MusicCaps
dev | test
GPT-4 Eval
The below is the overal performance:
The details of evaluation are as follows:
(Note: The evaluation results we present are based on the initial model of the original training framework. However, the scores showed some fluctuations after converting the framework to Huggingface. Here, we present our complete evaluation results, starting with the initial model results from the paper.)
Task
Dataset
Model
Performance
Metrics
Results
ASR
Librispeech
dev-clean | dev-other |
test-clean | test-other
SpeechT5
WER
2.1 | 5.5 | 2.4 | 5.8
SpeechNet
- | - | 30.7 | -
SLM-FT
- | - | 2.6 | 5.0
SALMONN
- | - | 2.1 | 4.9
SpeechVerse
- | - | 2.1 | 4.4
Qwen-Audio
1.8 | 4.0 | 2.0 | 4.2
Qwen2-Audio
1.3 | 3.4 | 1.6 | 3.6
Common Voice 15
en | zh | yue | fr
Whisper-large-v3
WER
9.3 | 12.8 | 10.9 | 10.8
Qwen2-Audio
8.6 | 6.9 | 5.9 | 9.6
Fleurs
zh
Whisper-large-v3
WER
7.7
Qwen2-Audio
7.5
Aishell2
Mic | iOS | Android
MMSpeech-base
WER
4.5 | 3.9 | 4.0
Paraformer-large
- | 2.9 | -
Qwen-Audio
3.3 | 3.1 | 3.3
Qwen2-Audio
3.0 | 3.0 | 2.9
S2TT
CoVoST2
en-de | de-en |
en-zh | zh-en
SALMONN
BLEU
18.6 | - | 33.1 | -
SpeechLLaMA
- | 27.1 | - | 12.3
BLSP
14.1 | - | - | -
Qwen-Audio
25.1 | 33.9 | 41.5 | 15.7
Qwen2-Audio
29.9 | 35.2 | 45.2 | 24.4
CoVoST2
es-en | fr-en | it-en |
SpeechLLaMA
BLEU
27.9 | 25.2 | 25.9
Qwen-Audio
39.7 | 38.5 | 36.0
Qwen2-Audio
40.0 | 38.5 | 36.3
SER
Meld
WavLM-large
ACC
0.542
Qwen-Audio
0.557
Qwen2-Audio
0.553
VSC
VocalSound
CLAP
ACC
0.4945
Pengi
0.6035
Qwen-Audio
0.9289
Qwen2-Audio
0.9392
AIR-Bench
Chat Benchmark
Speech | Sound |
Music | Mixed-Audio
SALMONN
BLSP
Pandagpt
Macaw-LLM
SpeechGPT
Next-gpt
Qwen-Audio
Gemini-1.5-pro
Qwen2-Audio
GPT-4
6.16 | 6.28 | 5.95 | 6.08
6.17 | 5.55 | 5.08 | 5.33
3.58 | 5.46 | 5.06 | 4.25
0.97 | 1.01 | 0.91 | 1.01
1.57 | 0.95 | 0.95 | 4.13
3.86 | 4.76 | 4.18 | 4.13
6.47 | 6.95 | 5.52 | 6.08
6.97 | 5.49 | 5.06 | 5.27
7.18 | 6.99 | 6.79 | 6.77
(Second is after converting huggingface)
Task
Dataset
Model
Performance
Metrics
Results
ASR
Librispeech
dev-clean | dev-other |
test-clean | test-other
SpeechT5
WER
2.1 | 5.5 | 2.4 | 5.8
SpeechNet
- | - | 30.7 | -
SLM-FT
- | - | 2.6 | 5.0
SALMONN
- | - | 2.1 | 4.9
SpeechVerse
- | - | 2.1 | 4.4
Qwen-Audio
1.8 | 4.0 | 2.0 | 4.2
Qwen2-Audio
1.7 | 3.6 | 1.7 | 4.0
Common Voice 15
en | zh | yue | fr
Whisper-large-v3
WER
9.3 | 12.8 | 10.9 | 10.8
Qwen2-Audio
8.7 | 6.5 | 5.9 | 9.6
Fleurs
zh
Whisper-large-v3
WER
7.7
Qwen2-Audio
7.0
Aishell2
Mic | iOS | Android
MMSpeech-base
WER
4.5 | 3.9 | 4.0
Paraformer-large
- | 2.9 | -
Qwen-Audio
3.3 | 3.1 | 3.3
Qwen2-Audio
3.2 | 3.1 | 2.9
S2TT
CoVoST2
en-de | de-en |
en-zh | zh-en
SALMONN
BLEU
18.6 | - | 33.1 | -
SpeechLLaMA
- | 27.1 | - | 12.3
BLSP
14.1 | - | - | -
Qwen-Audio
25.1 | 33.9 | 41.5 | 15.7
Qwen2-Audio
29.6 | 33.6 | 45.6 | 24.0
CoVoST2
es-en | fr-en | it-en |
SpeechLLaMA
BLEU
27.9 | 25.2 | 25.9
Qwen-Audio
39.7 | 38.5 | 36.0
Qwen2-Audio
38.7 | 37.2 | 35.2
SER
Meld
WavLM-large
ACC
0.542
Qwen-Audio
0.557
Qwen2-Audio
0.535
VSC
VocalSound
CLAP
ACC
0.4945
Pengi
0.6035
Qwen-Audio
0.9289
Qwen2-Audio
0.9395
AIR-Bench
Chat Benchmark
Speech | Sound |
Music | Mixed-Audio
SALMONN
BLSP
Pandagpt
Macaw-LLM
SpeechGPT
Next-gpt
Qwen-Audio
Gemini-1.5-pro
Qwen2-Audio
GPT-4
6.16 | 6.28 | 5.95 | 6.08
6.17 | 5.55 | 5.08 | 5.33
3.58 | 5.46 | 5.06 | 4.25
0.97 | 1.01 | 0.91 | 1.01
1.57 | 0.95 | 0.95 | 4.13
3.86 | 4.76 | 4.18 | 4.13
6.47 | 6.95 | 5.52 | 6.08
6.97 | 5.49 | 5.06 | 5.27
7.24 | 6.83 | 6.73 | 6.42
We have provided all evaluation scripts to reproduce our results. Please refer to eval_audio/EVALUATION.md for details.
Requirements
The code of Qwen2-Audio has been in the latest Hugging face transformers and we advise you to build from source with command pip install git+https://github.com/huggingface/transformers, or you might encounter the following error:
KeyError: 'qwen2-audio'
Quickstart
Below, we provide simple examples to show how to use Qwen2-Audio and Qwen2-Audio-Instruct with 🤗 Transformers. Before running the code, make sure you have setup the environment and installed the required packages. Make sure you meet the above requirements, and then install the dependent libraries. Now you can start with ModelScope or Transformers. Qwen2-Audio models currently perform best with audio clips under 30 seconds.
🤗 Transformers
In the following, we demonstrate how to use Qwen2-Audio-7B-Instruct for the inference, supporting both voice chat and audio analysis modes. Note that we have used the ChatML format for dialog, in this demo we show how to leverage apply_chat_template for this purpose.
Voice Chat Inference
In the voice chat mode, users can freely engage in voice interactions with Qwen2-Audio without text input:
from io import BytesIO
from urllib.request import urlopen
import librosa
from transformers import Qwen2AudioForConditionalGeneration, AutoProcessor
processor = AutoProcessor.from_pretrained("Qwen/Qwen2-Audio-7B-Instruct")
model = Qwen2AudioForConditionalGeneration.from_pretrained("Qwen/Qwen2-Audio-7B-Instruct", device_map="auto")
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"},
]},
]
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]
)
inputs = processor(text=text, audios=audios, return_tensors="pt", padding=True)
inputs.input_ids = inputs.input_ids.to("cuda")
generate_ids = model.generate(**inputs, max_length=256)
generate_ids = generate_ids[:, inputs.input_ids.size(1):]
response = processor.batch_decode(generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0]
Audio Analysis Inference
In the audio analysis, users could provide both audio and text instructions for analysis:
from io import BytesIO
from urllib.request import urlopen
import librosa
from transformers import Qwen2AudioForConditionalGeneration, AutoProcessor
processor = AutoProcessor.from_pretrained("Qwen/Qwen2-Audio-7B-Instruct")
model = Qwen2AudioForConditionalGeneration.from_pretrained("Qwen/Qwen2-Audio-7B-Instruct", device_map="auto")
conversation = [
{'role': 'system', 'content': 'You are a helpful assistant.'},
{"role": "user", "content": [
{"type": "audio", "audio_url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen2-Audio/audio/glass-breaking-151256.mp3"},
{"type": "text", "text": "What's that sound?"},
]},
{"role": "assistant", "content": "It is the sound of glass shattering."},
{"role": "user", "content": [
{"type": "text", "text": "What can you do when you hear that?"},
]},
{"role": "assistant", "content": "Stay alert and cautious, and check if anyone is hurt or if there is any damage to property."},
{"role": "user", "content": [
{"type": "audio", "audio_url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen2-Audio/audio/1272-128104-0000.flac"},
{"type": "text", "text": "What does the person say?"},
]},
]
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]
)
inputs = processor(text=text, audios=audios, return_tensors="pt", padding=True)
inputs.input_ids = inputs.input_ids.to("cuda")
generate_ids = model.generate(**inputs, max_length=256)
generate_ids = generate_ids[:, inputs.input_ids.size(1):]
response = processor.batch_decode(generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0]
Batch Inference
We also support batch inference:
from io import BytesIO
from urllib.request import urlopen
import librosa
from transformers import Qwen2AudioForConditionalGeneration, AutoProcessor
processor = AutoProcessor.from_pretrained("Qwen/Qwen2-Audio-7B-Instruct")
model = Qwen2AudioForConditionalGeneration.from_pretrained("Qwen/Qwen2-Audio-7B-Instruct", device_map="auto")
conversation1 = [
{"role": "user", "content": [
{"type": "audio", "audio_url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen2-Audio/audio/glass-breaking-151256.mp3"},
{"type": "text", "text": "What's that sound?"},
]},
{"role": "assistant", "content": "It is the sound of glass shattering."},
{"role": "user", "content": [
{"type": "audio", "audio_url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen2-Audio/audio/f2641_0_throatclearing.wav"},
{"type": "text", "text": "What can you hear?"},
]}
]
conversation2 = [
{"role": "user", "content": [
{"type": "audio", "audio_url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen2-Audio/audio/1272-128104-0000.flac"},
{"type": "text", "text": "What does the person say?"},
]},
]
conversations = [conversation1, conversation2]
text = [processor.apply_chat_template(conversation, add_generation_prompt=True, tokenize=False) for conversation in conversations]
audios = []
for conversation in conversations:
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]
)
inputs = processor(text=text, audios=audios, return_tensors="pt", padding=True)
inputs['input_ids'] = inputs['input_ids'].to("cuda")
inputs.input_ids = inputs.input_ids.to("cuda")
generate_ids = model.generate(**inputs, max_length=256)
generate_ids = generate_ids[:, inputs.input_ids.size(1):]
response = processor.batch_decode(generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)
Running Qwen2-Audio pretrained base model is also simple.
from io import BytesIO
from urllib.request import urlopen
import librosa
from transformers import AutoProcessor, Qwen2AudioForConditionalGeneration
model = Qwen2AudioForConditionalGeneration.from_pretrained("Qwen/Qwen2-Audio-7B" ,trust_remote_code=True)
processor = AutoProcessor.from_pretrained("Qwen/Qwen2-Audio-7B" ,trust_remote_code=True)
prompt = "<|audio_bos|><|AUDIO|><|audio_eos|>Generate the caption in English:"
url = "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"
audio, sr = librosa.load(BytesIO(urlopen(url).read()), sr=processor.feature_extractor.sampling_rate)
inputs = processor(text=prompt, audios=audio, return_tensors="pt")
generated_ids = model.generate(**inputs, max_length=256)
generated_ids = generated_ids[:, inputs.input_ids.size(1):]
response = processor.batch_decode(generated_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0]
🤖 ModelScope
We strongly advise users especially those in mainland China to use ModelScope. snapshot_download can help you solve issues concerning downloading checkpoints.
Demo
Web UI
We provide code for users to build a web UI demo. Before you start, make sure you install the following packages:
pip install -r requirements_web_demo.txt
Then run the command below and click on the generated link:
python demo/web_demo_audio.py
demos
More impressive cases will be updated on our blog at Qwen's blog.
We Are Hiring
If you are interested in joining us as full-time or intern, please contact us at [email protected].
License Agreement
Check the license of each model inside its HF repo. It is NOT necessary for you to submit a request for commercial usage.
Citation
If you find our paper and code useful in your research, please consider giving a star :star: and citation :pencil: :)
@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}
}
@article{Qwen2-Audio,
title={Qwen2-Audio Technical Report},
author={Chu, Yunfei and Xu, Jin and Yang, Qian and Wei, Haojie and Wei, Xipin and Guo, Zhifang and Leng, Yichong and Lv, Yuanjun and He, Jinzheng and Lin, Junyang and Zhou, Chang and Zhou, Jingren},
journal={arXiv preprint arXiv:2407.10759},
year={2024}
}
Contact Us
If you are interested to leave a message to either our research team or product team, feel free to send an email to [email protected].