Safetensors
qwen2_5_omni
nielsr HF Staff commited on
Commit
e0049d6
·
verified ·
1 Parent(s): 40da49a

Add pipeline tag and library name

Browse files

This PR adds the `pipeline_tag: audio-text-to-text` and `library_name: transformers` metadata to improve model discoverability and usability.

Files changed (1) hide show
  1. README.md +10 -7
README.md CHANGED
@@ -1,9 +1,11 @@
1
  ---
2
- license: apache-2.0
3
- datasets:
4
- - amaai-lab/MusicBench
5
  base_model:
6
  - Qwen/Qwen2.5-Omni-7B
 
 
 
 
 
7
  ---
8
 
9
  # Ke-Omni-R: Achieving Advanced Audio Reasoning with a Concise 50-Words Think Process
@@ -19,7 +21,7 @@ Ke-Omni-R is an advanced audio reasoning model built upon [Qwen2.5-Omni-7B](http
19
 
20
  ## Performance: Accuracies (%) on MMAU Test-mini and Test benchmark
21
  | Model | Method | Sound (Test-mini) | Sound (Test) | Music (Test-mini) | Music (Test) | Speech (Test-mini) | Speech (Test) | Average (Test-mini) | Average (Test) |
22
- |---------------------------------------|-----------------------|-----------|-------|-----------|-------|-----------|------|------------|-------|
23
  | - | Human\* | 86.31 | - | 78.22 | - | 82.17 | - | 82.23 | - |
24
  | Gemini Pro 2.0 Flash | Direct Inference\* | 56.46 | 61.73 | 58.68 | 56.53 | 51.65 | 61.53 | 55.60 | 59.93 |
25
  | Audio Flamingo 2 | Direct Inference\* | 61.56 | 65.10 | **73.95** |**72.90**| 30.93 | 40.26 | 55.48 | 59.42 |
@@ -80,7 +82,9 @@ print(completions)
80
 
81
  the output should be
82
  ```
83
- ["Well, it sounds like there's a car accelerating. You can hear the engine revving up, and there's a bit of a thump or thud sound too. It might be the car hitting something or just a part of the acceleration process. It gives off a sense of speed and power. What do you think about it? Do you have any other audio samples you want to talk about?", '<think>The audio features a vehicle accelerating and revving, which is characteristic of a car. The sound is consistent with a car engine, not an aircraft, tank, or missile.</think>\n<answer>Car</answer>', "<think>The main source of sound is a buzzing insect, which is consistent with the size and sound of a honeybee. The other options don't match the sound or context.</think>\n<answer>honeybee</answer>"]
 
 
84
  ```
85
 
86
  ## Acknowledgements
@@ -102,5 +106,4 @@ We express our gratitude to the following projects and teams for their contribut
102
  publisher = {GitHub},
103
  journal = {GitHub Repository},
104
  howpublished = {\url{https://github.com/shuaijiang/Ke-Omni-R}},
105
- }
106
- ```
 
1
  ---
 
 
 
2
  base_model:
3
  - Qwen/Qwen2.5-Omni-7B
4
+ datasets:
5
+ - amaai-lab/MusicBench
6
+ license: apache-2.0
7
+ pipeline_tag: audio-text-to-text
8
+ library_name: transformers
9
  ---
10
 
11
  # Ke-Omni-R: Achieving Advanced Audio Reasoning with a Concise 50-Words Think Process
 
21
 
22
  ## Performance: Accuracies (%) on MMAU Test-mini and Test benchmark
23
  | Model | Method | Sound (Test-mini) | Sound (Test) | Music (Test-mini) | Music (Test) | Speech (Test-mini) | Speech (Test) | Average (Test-mini) | Average (Test) |
24
+ |---------------------------------------|----------------اريات-------|-----------|-------|-----------|-------|-----------|------|------------|-------|
25
  | - | Human\* | 86.31 | - | 78.22 | - | 82.17 | - | 82.23 | - |
26
  | Gemini Pro 2.0 Flash | Direct Inference\* | 56.46 | 61.73 | 58.68 | 56.53 | 51.65 | 61.53 | 55.60 | 59.93 |
27
  | Audio Flamingo 2 | Direct Inference\* | 61.56 | 65.10 | **73.95** |**72.90**| 30.93 | 40.26 | 55.48 | 59.42 |
 
82
 
83
  the output should be
84
  ```
85
+ ["Well, it sounds like there's a car accelerating. You can hear the engine revving up, and there's a bit of a thump or thud sound too. It might be the car hitting something or just a part of the acceleration process. It gives off a sense of speed and power. What do you think about it? Do you have any other audio samples you want to talk about?", '<think>The audio features a vehicle accelerating and revving, which is characteristic of a car. The sound is consistent with a car engine, not an aircraft, tank, or missile.</think>
86
+ <answer>Car</answer>', "<think>The main source of sound is a buzzing insect, which is consistent with the size and sound of a honeybee. The other options don't match the sound or context.</think>
87
+ <answer>honeybee</answer>"]
88
  ```
89
 
90
  ## Acknowledgements
 
106
  publisher = {GitHub},
107
  journal = {GitHub Repository},
108
  howpublished = {\url{https://github.com/shuaijiang/Ke-Omni-R}},
109
+ }