File size: 4,849 Bytes
00f19b9
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
137
138
139
140
141

from argparse import ArgumentParser

def parse_args():
    parser = ArgumentParser(description="Whisper FastAPI Online Server")
    parser.add_argument(
        "--host",
        type=str,
        default="localhost",
        help="The host address to bind the server to.",
    )
    parser.add_argument(
        "--port", type=int, default=8000, help="The port number to bind the server to."
    )
    parser.add_argument(
        "--warmup-file",
        type=str,
        default=None,
        dest="warmup_file",
        help="""
        The path to a speech audio wav file to warm up Whisper so that the very first chunk processing is fast.
        If not set, uses https://github.com/ggerganov/whisper.cpp/raw/master/samples/jfk.wav.
        If False, no warmup is performed.
        """,
    )

    parser.add_argument(
        "--confidence-validation",
        action="store_true",
        help="Accelerates validation of tokens using confidence scores. Transcription will be faster but punctuation might be less accurate.",
    )

    parser.add_argument(
        "--diarization",
        action="store_true",
        default=False,
        help="Enable speaker diarization.",
    )

    parser.add_argument(
        "--no-transcription",
        action="store_true",
        help="Disable transcription to only see live diarization results.",
    )
    
    parser.add_argument(
        "--min-chunk-size",
        type=float,
        default=0.5,
        help="Minimum audio chunk size in seconds. It waits up to this time to do processing. If the processing takes shorter time, it waits, otherwise it processes the whole segment that was received by this time.",
    )
    
    parser.add_argument(
        "--model",
        type=str,
        default="tiny",
        help="Name size of the Whisper model to use (default: tiny). Suggested values: tiny.en,tiny,base.en,base,small.en,small,medium.en,medium,large-v1,large-v2,large-v3,large,large-v3-turbo. The model is automatically downloaded from the model hub if not present in model cache dir.",
    )
    
    parser.add_argument(
        "--model_cache_dir",
        type=str,
        default=None,
        help="Overriding the default model cache dir where models downloaded from the hub are saved",
    )
    parser.add_argument(
        "--model_dir",
        type=str,
        default=None,
        help="Dir where Whisper model.bin and other files are saved. This option overrides --model and --model_cache_dir parameter.",
    )
    parser.add_argument(
        "--lan",
        "--language",
        type=str,
        default="auto",
        help="Source language code, e.g. en,de,cs, or 'auto' for language detection.",
    )
    parser.add_argument(
        "--task",
        type=str,
        default="transcribe",
        choices=["transcribe", "translate"],
        help="Transcribe or translate.",
    )
    parser.add_argument(
        "--backend",
        type=str,
        default="faster-whisper",
        choices=["faster-whisper", "whisper_timestamped", "mlx-whisper", "openai-api"],
        help="Load only this backend for Whisper processing.",
    )
    parser.add_argument(
        "--vac",
        action="store_true",
        default=False,
        help="Use VAC = voice activity controller. Recommended. Requires torch.",
    )
    parser.add_argument(
        "--vac-chunk-size", type=float, default=0.04, help="VAC sample size in seconds."
    )

    parser.add_argument(
        "--no-vad",
        action="store_true",
        help="Disable VAD (voice activity detection).",
    )
    
    parser.add_argument(
        "--buffer_trimming",
        type=str,
        default="segment",
        choices=["sentence", "segment"],
        help='Buffer trimming strategy -- trim completed sentences marked with punctuation mark and detected by sentence segmenter, or the completed segments returned by Whisper. Sentence segmenter must be installed for "sentence" option.',
    )
    parser.add_argument(
        "--buffer_trimming_sec",
        type=float,
        default=15,
        help="Buffer trimming length threshold in seconds. If buffer length is longer, trimming sentence/segment is triggered.",
    )
    parser.add_argument(
        "-l",
        "--log-level",
        dest="log_level",
        choices=["DEBUG", "INFO", "WARNING", "ERROR", "CRITICAL"],
        help="Set the log level",
        default="DEBUG",
    )
    parser.add_argument("--ssl-certfile", type=str, help="Path to the SSL certificate file.", default=None)
    parser.add_argument("--ssl-keyfile", type=str, help="Path to the SSL private key file.", default=None)


    args = parser.parse_args()
    
    args.transcription = not args.no_transcription
    args.vad = not args.no_vad    
    delattr(args, 'no_transcription')
    delattr(args, 'no_vad')
    
    return args