| | |
|---|
| | | type=str, |
|---|
| | | default="5, 10, 5", |
|---|
| | | help="chunk") |
|---|
| | | parser.add_argument("--encoder_chunk_look_back", |
|---|
| | | type=int, |
|---|
| | | default=4, |
|---|
| | | help="number of chunks to lookback for encoder self-attention") |
|---|
| | | parser.add_argument("--decoder_chunk_look_back", |
|---|
| | | type=int, |
|---|
| | | default=1, |
|---|
| | | help="number of encoder chunks to lookback for decoder cross-attention") |
|---|
| | | parser.add_argument("--chunk_interval", |
|---|
| | | type=int, |
|---|
| | | default=10, |
|---|
| | |
|---|
| | | input=True, |
|---|
| | | frames_per_buffer=CHUNK) |
|---|
| | | |
|---|
| | | message = json.dumps({"mode": args.mode, "chunk_size": args.chunk_size, "chunk_interval": args.chunk_interval, |
|---|
| | | message = json.dumps({"mode": args.mode, "chunk_size": args.chunk_size, "encoder_chunk_look_back": args.encoder_chunk_look_back, |
|---|
| | | "decoder_chunk_look_back": args.decoder_chunk_look_back, "chunk_interval": args.chunk_interval, |
|---|
| | | "wav_name": "microphone", "is_speaking": True}) |
|---|
| | | #voices.put(message) |
|---|
| | | await websocket.send(message) |
|---|
| | |
|---|
| | | |
|---|
| | | meg = await websocket.recv() |
|---|
| | | meg = json.loads(meg) |
|---|
| | | # print(meg) |
|---|
| | | wav_name = meg.get("wav_name", "demo") |
|---|
| | | text = meg["text"] |
|---|
| | | |
|---|
| | |
|---|
| | | # text_print = text_print[-args.words_max_print:] |
|---|
| | | # os.system('clear') |
|---|
| | | print("\rpid" + str(id) + ": " + wav_name + ": " + text_print) |
|---|
| | | offline_msg_done = True |
|---|
| | | 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) |
|---|
