| | |
|---|
| | | 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": |
|---|
| | |
|---|
| | | 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}') |
|---|
| | | # 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: |
|---|
