aha 0.2.6

aha model inference library, now supports Qwen(2.5VL/3/3VL/3.5/ASR/3Embedding/3Reranker), MiniCPM(4/5), VoxCPM(0.5B/1.5/2), DeepSeek-OCR/2, Hunyuan-OCR, PaddleOCR-VL/1.5, RMBG2.0, GLM(ASR-Nano-2512/OCR), Fun-ASR-Nano-2512, LFM(2/2.5/2VL/2.5VL)
Documentation 
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

pub struct FireRedVadConfig {
    pub smooth_window_size: usize,
    pub speech_threshold: f32,
    pub singing_threshold: f32,
    pub music_threshold: f32,
    pub pad_start_frame: usize,
    pub min_speech_frame: usize,
    pub max_speech_frame: usize,
    pub min_event_frame: usize,
    pub max_event_frame: usize,
    pub min_silence_frame: usize,
    pub merge_silence_frame: usize,
    pub extend_speech_frame: usize,
    pub chunk_max_frame: usize,
}

impl FireRedVadConfig {
    pub fn default_vad() -> Self {
        Self {
            smooth_window_size: 5,
            speech_threshold: 0.4,
            singing_threshold: 0.5,
            music_threshold: 0.5,
            pad_start_frame: 5,
            min_speech_frame: 20,
            max_speech_frame: 2000,
            min_event_frame: 20,
            max_event_frame: 2000,
            min_silence_frame: 20,
            merge_silence_frame: 0,
            extend_speech_frame: 0,
            chunk_max_frame: 30000,
        }
    }

    pub fn default_stream_vad() -> Self {
        Self {
            smooth_window_size: 1,
            speech_threshold: 0.5,
            singing_threshold: 0.5,
            music_threshold: 0.5,
            pad_start_frame: 5,
            min_speech_frame: 8,
            max_speech_frame: 2000,
            min_event_frame: 20,
            max_event_frame: 2000,
            min_silence_frame: 20,
            merge_silence_frame: 0,
            extend_speech_frame: 0,
            chunk_max_frame: 30000,
        }
    }

    pub fn default_aed() -> Self {
        Self {
            smooth_window_size: 5,
            speech_threshold: 0.4,
            singing_threshold: 0.5,
            music_threshold: 0.5,
            pad_start_frame: 5,
            min_speech_frame: 8,
            max_speech_frame: 2000,
            min_event_frame: 20,
            max_event_frame: 2000,
            min_silence_frame: 20,
            merge_silence_frame: 0,
            extend_speech_frame: 0,
            chunk_max_frame: 30000,
        }
    }
}

#[derive(Debug, Clone, PartialEq, serde::Deserialize)]
pub struct CMVNData {
    pub cmvn: Vec<Vec<f32>>,
}

pub struct DetectModelConfig {
    pub idim: usize,
    pub r: usize,
    pub m: usize,
    pub h: usize,
    pub p: usize,
    pub n1: usize,
    pub s1: usize,
    pub n2: usize,
    pub s2: usize,
    pub odim: usize,
}

impl DetectModelConfig {
    pub fn default_vad() -> Self {
        Self {
            idim: 80,
            r: 8,
            m: 1,
            h: 256,
            p: 128,
            n1: 20,
            s1: 1,
            n2: 20,
            s2: 1,
            odim: 1,
        }
    }

    pub fn default_stream_vad() -> Self {
        Self {
            idim: 80,
            r: 8,
            m: 1,
            h: 256,
            p: 128,
            n1: 20,
            s1: 1,
            n2: 0,
            s2: 1,
            odim: 1,
        }
    }

    pub fn default_aed() -> Self {
        Self {
            idim: 80,
            r: 8,
            m: 1,
            h: 256,
            p: 128,
            n1: 20,
            s1: 1,
            n2: 20,
            s2: 1,
            odim: 3,
        }
    }
}