| | |
|---|
| | | import json |
|---|
| | | import traceback |
|---|
| | | from multiprocessing import Process |
|---|
| | | from funasr.fileio.datadir_writer import DatadirWriter |
|---|
| | | # from funasr.fileio.datadir_writer import DatadirWriter |
|---|
| | | |
|---|
| | | import logging |
|---|
| | | |
|---|
| | | SUPPORT_AUDIO_TYPE_SETS = ['.wav', '.pcm'] |
|---|
| | | logging.basicConfig(level=logging.ERROR) |
|---|
| | | |
|---|
| | | parser = argparse.ArgumentParser() |
|---|
| | |
|---|
| | | |
|---|
| | | voices = Queue() |
|---|
| | | offline_msg_done=False |
|---|
| | | |
|---|
| | | ibest_writer = None |
|---|
| | | |
|---|
| | | if args.output_dir is not None: |
|---|
| | | writer = DatadirWriter(args.output_dir) |
|---|
| | | ibest_writer = writer[f"1best_recog"] |
|---|
| | | # if os.path.exists(args.output_dir): |
|---|
| | | # os.remove(args.output_dir) |
|---|
| | | |
|---|
| | | if not os.path.exists(args.output_dir): |
|---|
| | | os.makedirs(args.output_dir) |
|---|
| | | |
|---|
| | | |
|---|
| | | async def record_microphone(): |
|---|
| | |
|---|
| | | frames = wav_file.readframes(wav_file.getnframes()) |
|---|
| | | audio_bytes = bytes(frames) |
|---|
| | | else: |
|---|
| | | raise NotImplementedError( |
|---|
| | | f'Not supported audio type') |
|---|
| | | import ffmpeg |
|---|
| | | try: |
|---|
| | | # This launches a subprocess to decode audio while down-mixing and resampling as necessary. |
|---|
| | | # Requires the ffmpeg CLI and `ffmpeg-python` package to be installed. |
|---|
| | | audio_bytes, _ = ( |
|---|
| | | ffmpeg.input(wav_path, threads=0) |
|---|
| | | .output("-", format="s16le", acodec="pcm_s16le", ac=1, ar=16000) |
|---|
| | | .run(cmd=["ffmpeg", "-nostdin"], capture_stdout=True, capture_stderr=True) |
|---|
| | | ) |
|---|
| | | except ffmpeg.Error as e: |
|---|
| | | raise RuntimeError(f"Failed to load audio: {e.stderr.decode()}") from e |
|---|
| | | |
|---|
| | | # stride = int(args.chunk_size/1000*16000*2) |
|---|
| | | stride = int(60 * args.chunk_size[1] / args.chunk_interval / 1000 * 16000 * 2) |
|---|
| | |
|---|
| | | sleep_duration = 0.001 if args.mode == "offline" else 60 * args.chunk_size[1] / args.chunk_interval / 1000 |
|---|
| | | |
|---|
| | | await asyncio.sleep(sleep_duration) |
|---|
| | | # when all data sent, we need to close websocket |
|---|
| | | while not voices.empty(): |
|---|
| | | await asyncio.sleep(1) |
|---|
| | | await asyncio.sleep(3) |
|---|
| | | |
|---|
| | | if not args.mode=="offline": |
|---|
| | | await asyncio.sleep(2) |
|---|
| | | # offline model need to wait for message recved |
|---|
| | | |
|---|
| | | if args.mode=="offline": |
|---|
| | |
|---|
| | | text_print = "" |
|---|
| | | text_print_2pass_online = "" |
|---|
| | | text_print_2pass_offline = "" |
|---|
| | | if args.output_dir is not None: |
|---|
| | | ibest_writer = open(os.path.join(args.output_dir, "text.{}".format(id)), "a", encoding="utf-8") |
|---|
| | | else: |
|---|
| | | ibest_writer = None |
|---|
| | | try: |
|---|
| | | while True: |
|---|
| | | |
|---|
| | | meg = await websocket.recv() |
|---|
| | | meg = json.loads(meg) |
|---|
| | | # print(meg) |
|---|
| | | wav_name = meg.get("wav_name", "demo") |
|---|
| | | text = meg["text"] |
|---|
| | | if ibest_writer is not None: |
|---|
| | | ibest_writer["text"][wav_name] = text |
|---|
| | | |
|---|
| | | if ibest_writer is not None: |
|---|
| | | text_write_line = "{}\t{}\n".format(wav_name, text) |
|---|
| | | ibest_writer.write(text_write_line) |
|---|
| | | |
|---|
| | | if meg["mode"] == "online": |
|---|
| | | text_print += "{}".format(text) |
|---|
| | | text_print = text_print[-args.words_max_print:] |
|---|
| | | # os.system('clear') |
|---|
| | | os.system('clear') |
|---|
| | | print("\rpid" + str(id) + ": " + text_print) |
|---|
| | | elif meg["mode"] == "offline": |
|---|
| | | text_print += "{}".format(text) |
|---|
| | | text_print = text_print[-args.words_max_print:] |
|---|
| | | # text_print = text_print[-args.words_max_print:] |
|---|
| | | # os.system('clear') |
|---|
| | | print("\rpid" + str(id) + ": " + text_print) |
|---|
| | | offline_msg_done=True |
|---|
| | | print("\rpid" + str(id) + ": " + wav_name + ": " + text_print) |
|---|
| | | if ("is_final" in meg and meg["is_final"]==False): |
|---|
| | | offline_msg_done = True |
|---|
| | | |
|---|
| | | if not "is_final" in meg: |
|---|
| | | offline_msg_done = True |
|---|
| | | else: |
|---|
| | | if meg["mode"] == "2pass-online": |
|---|
| | | text_print_2pass_online += "{}".format(text) |
|---|
| | |
|---|
| | | text_print = text_print_2pass_offline + "{}".format(text) |
|---|
| | | text_print_2pass_offline += "{}".format(text) |
|---|
| | | text_print = text_print[-args.words_max_print:] |
|---|
| | | # os.system('clear') |
|---|
| | | os.system('clear') |
|---|
| | | print("\rpid" + str(id) + ": " + text_print) |
|---|
| | | offline_msg_done=True |
|---|
| | | |
|---|
| | |
|---|
| | | |
|---|
| | | |
|---|
| | | |
|---|
| | | async def print_messge(): |
|---|
| | | global websocket |
|---|
| | | while True: |
|---|
| | | try: |
|---|
| | | meg = await websocket.recv() |
|---|
| | | meg = json.loads(meg) |
|---|
| | | print(meg) |
|---|
| | | except Exception as e: |
|---|
| | | print("Exception:", e) |
|---|
| | | #traceback.print_exc() |
|---|
| | | exit(0) |
|---|
| | | |
|---|
| | | async def ws_client(id, chunk_begin, chunk_size): |
|---|
| | | if args.audio_in is None: |
|---|
| | |
|---|
| | | wav_name = wav_splits[0] if len(wav_splits) > 1 else "demo" |
|---|
| | | wav_path = wav_splits[1] if len(wav_splits) > 1 else wav_splits[0] |
|---|
| | | audio_type = os.path.splitext(wav_path)[-1].lower() |
|---|
| | | if audio_type not in SUPPORT_AUDIO_TYPE_SETS: |
|---|
| | | raise NotImplementedError( |
|---|
| | | f'Not supported audio type: {audio_type}') |
|---|
| | | |
|---|
| | | |
|---|
| | | total_len = len(wavs) |
|---|
| | | if total_len >= args.thread_num: |
|---|
