Audio Classification
Transformers
Safetensors
Chinese
qwen2_audio
text2text-generation
leo98xh commited on
Commit
80aad27
·
verified ·
1 Parent(s): 9fd670d

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +6 -6
README.md CHANGED
@@ -5,8 +5,8 @@ language:
5
  base_model:
6
  - Qwen/Qwen2-Audio-7B-Instruct
7
  datasets:
8
- - AudioTuring/Audio-Turing-Test-Audios
9
- - AudioTuring/Audio-Turing-Test-Corpus
10
  pipeline_tag: audio-classification
11
  library_name: transformers
12
  ---
@@ -21,16 +21,16 @@ library_name: transformers
21
 
22
  ## About Audio Turing Test (ATT)
23
 
24
- ATT is an evaluation framework with a standardized human evaluation protocol and an accompanying dataset, aiming to resolve the lack of unified protocols in TTS evaluation and the difficulty in comparing multiple TTS systems. To further support the training and iteration of TTS systems, we utilized additional private evaluation data to train Auto-ATT model based on Qwen2-Audio-7B, enabling a model-as-a-judge approach for rapid evaluation of TTS systems on the ATT dataset. The datasets and Auto-ATT model can be cound in [ATT Collection](https://huggingface.co/collections/AudioTuring/audio-turing-test-6826e24d2197bf91fae6d7f5).
25
 
26
 
27
  ## Usage
28
 
29
- [Inference Code](https://github.com/AudioTuring/Auto-ATT-Inference)
30
 
31
 
32
  ## Datasets & Benchmarks
33
- See [ATT Collection](https://huggingface.co/collections/AudioTuring/audio-turing-test-6826e24d2197bf91fae6d7f5).
34
 
35
 
36
 
@@ -41,7 +41,7 @@ See [ATT Collection](https://huggingface.co/collections/AudioTuring/audio-turing
41
  author = {Wang, Xihuai and Zhao, Ziyi and Ren, Siyu and Zhang, Shao and Li, Song and Li, Xiaoyu and Wang, Ziwen and Qiu, Lin and Wan, Guanglu and Cao, Xuezhi and Cai, Xunliang and Zhang, Weinan},
42
  title = {Audio Turing Test: Benchmarking the Human-likeness and Naturalness of Large Language Model-based Text-to-Speech Systems in Chinese},
43
  year = {2025},
44
- url = {https://huggingface.co/AudioTuring/Auto-ATT},
45
  publisher = {huggingface},
46
  }
47
  ```
 
5
  base_model:
6
  - Qwen/Qwen2-Audio-7B-Instruct
7
  datasets:
8
+ - Meituan/Audio-Turing-Test-Audios
9
+ - Meituan/Audio-Turing-Test-Corpus
10
  pipeline_tag: audio-classification
11
  library_name: transformers
12
  ---
 
21
 
22
  ## About Audio Turing Test (ATT)
23
 
24
+ ATT is an evaluation framework with a standardized human evaluation protocol and an accompanying dataset, aiming to resolve the lack of unified protocols in TTS evaluation and the difficulty in comparing multiple TTS systems. To further support the training and iteration of TTS systems, we utilized additional private evaluation data to train Auto-ATT model based on Qwen2-Audio-7B, enabling a model-as-a-judge approach for rapid evaluation of TTS systems on the ATT dataset. The datasets and Auto-ATT model can be cound in [ATT Collection](https://huggingface.co/collections/meituan/audio-turing-test-682446320368164faeaf38a4).
25
 
26
 
27
  ## Usage
28
 
29
+ [Inference Code](https://github.com/Meituan/Auto-ATT-Inference)
30
 
31
 
32
  ## Datasets & Benchmarks
33
+ See [ATT Collection](https://huggingface.co/collections/meituan/audio-turing-test-682446320368164faeaf38a4).
34
 
35
 
36
 
 
41
  author = {Wang, Xihuai and Zhao, Ziyi and Ren, Siyu and Zhang, Shao and Li, Song and Li, Xiaoyu and Wang, Ziwen and Qiu, Lin and Wan, Guanglu and Cao, Xuezhi and Cai, Xunliang and Zhang, Weinan},
42
  title = {Audio Turing Test: Benchmarking the Human-likeness and Naturalness of Large Language Model-based Text-to-Speech Systems in Chinese},
43
  year = {2025},
44
+ url = {https://huggingface.co/Meituan/Auto-ATT},
45
  publisher = {huggingface},
46
  }
47
  ```