File size: 5,380 Bytes
372bf52
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
#!/usr/bin/env python3
import sys
import numpy as np
import librosa
from functools import lru_cache
import time
import logging

logger = logging.getLogger(__name__)

from src.whisper_streaming.whisper_online import *

@lru_cache(10**6)
def load_audio(fname):
    a, _ = librosa.load(fname, sr=16000, dtype=np.float32)
    return a


def load_audio_chunk(fname, beg, end):
    audio = load_audio(fname)
    beg_s = int(beg * 16000)
    end_s = int(end * 16000)
    return audio[beg_s:end_s]

if __name__ == "__main__":

    import argparse

    parser = argparse.ArgumentParser()
    parser.add_argument(
        "--audio_path",
        type=str,
        default='samples_jfk.wav',
        help="Filename of 16kHz mono channel wav, on which live streaming is simulated.",
    )
    add_shared_args(parser)
    parser.add_argument(
        "--start_at",
        type=float,
        default=0.0,
        help="Start processing audio at this time.",
    )
    parser.add_argument(
        "--offline", action="store_true", default=False, help="Offline mode."
    )
    parser.add_argument(
        "--comp_unaware",
        action="store_true",
        default=False,
        help="Computationally unaware simulation.",
    )

    args = parser.parse_args()

    # reset to store stderr to different file stream, e.g. open(os.devnull,"w")
    logfile = None # sys.stderr

    if args.offline and args.comp_unaware:
        logger.error(
            "No or one option from --offline and --comp_unaware are available, not both. Exiting."
        )
        sys.exit(1)

    #    if args.log_level:
    #        logging.basicConfig(format='whisper-%(levelname)s:%(name)s: %(message)s',
    #                            level=getattr(logging, args.log_level))

    set_logging(args, logger,others=["src.whisper_streaming.online_asr"])

    audio_path = args.audio_path

    SAMPLING_RATE = 16000
    duration = len(load_audio(audio_path)) / SAMPLING_RATE
    logger.info("Audio duration is: %2.2f seconds" % duration)

    asr, online = asr_factory(args, logfile=logfile)
    if args.vac:
        min_chunk = args.vac_chunk_size
    else:
        min_chunk = args.min_chunk_size

    # load the audio into the LRU cache before we start the timer
    a = load_audio_chunk(audio_path, 0, 1)

    # warm up the ASR because the very first transcribe takes much more time than the other
    asr.transcribe(a)

    beg = args.start_at
    start = time.time() - beg

    def output_transcript(o, now=None):
        # output format in stdout is like:
        # 4186.3606 0 1720 Takhle to je
        # - the first three words are:
        #    - emission time from beginning of processing, in milliseconds
        #    - beg and end timestamp of the text segment, as estimated by Whisper model. The timestamps are not accurate, but they're useful anyway
        # - the next words: segment transcript
        if now is None:
            now = time.time() - start
        if o[0] is not None:
            log_string = f"{now*1000:1.0f}, {o[0]*1000:1.0f}-{o[1]*1000:1.0f} ({(now-o[1]):+1.0f}s): {o[2]}"

            logger.debug(
                log_string
            )

            if logfile is not None:
                print(
                    log_string,
                    file=logfile,
                    flush=True,
                )
        else:
            # No text, so no output
            pass

    if args.offline:  ## offline mode processing (for testing/debugging)
        a = load_audio(audio_path)
        online.insert_audio_chunk(a)
        try:
            o = online.process_iter()
        except AssertionError as e:
            logger.error(f"assertion error: {repr(e)}")
        else:
            output_transcript(o)
        now = None
    elif args.comp_unaware:  # computational unaware mode
        end = beg + min_chunk
        while True:
            a = load_audio_chunk(audio_path, beg, end)
            online.insert_audio_chunk(a)
            try:
                o = online.process_iter()
            except AssertionError as e:
                logger.error(f"assertion error: {repr(e)}")
                pass
            else:
                output_transcript(o, now=end)

            logger.debug(f"## last processed {end:.2f}s")

            if end >= duration:
                break

            beg = end

            if end + min_chunk > duration:
                end = duration
            else:
                end += min_chunk
        now = duration

    else:  # online = simultaneous mode
        end = 0
        while True:
            now = time.time() - start
            if now < end + min_chunk:
                time.sleep(min_chunk + end - now)
            end = time.time() - start
            a = load_audio_chunk(audio_path, beg, end)
            beg = end
            online.insert_audio_chunk(a)

            try:
                o = online.process_iter()
            except AssertionError as e:
                logger.error(f"assertion error: {e}")
                pass
            else:
                output_transcript(o)
            now = time.time() - start
            logger.debug(
                f"## last processed {end:.2f} s, now is {now:.2f}, the latency is {now-end:.2f}"
            )

            if end >= duration:
                break
        now = None

    o = online.finish()
    output_transcript(o, now=now)