From b9bcf1f093c3053fdc4e2cf4a1d38e27bbf429fb Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期四, 19 十月 2023 14:03:48 +0800
Subject: [PATCH] docs
---
funasr/runtime/python/websocket/funasr_wss_client.py | 84 +++++++++++++++++++++++++-----------------
1 files changed, 50 insertions(+), 34 deletions(-)
diff --git a/funasr/runtime/python/websocket/funasr_wss_client.py b/funasr/runtime/python/websocket/funasr_wss_client.py
index fc4d516..f4f35bb 100644
--- a/funasr/runtime/python/websocket/funasr_wss_client.py
+++ b/funasr/runtime/python/websocket/funasr_wss_client.py
@@ -8,11 +8,10 @@
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()
@@ -30,6 +29,14 @@
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,
@@ -72,11 +79,13 @@
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():
@@ -98,7 +107,8 @@
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)
@@ -136,8 +146,17 @@
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)
@@ -166,10 +185,9 @@
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":
@@ -186,27 +204,38 @@
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)
@@ -216,7 +245,7 @@
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
@@ -227,17 +256,6 @@
-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:
@@ -290,9 +308,7 @@
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:
--
Gitblit v1.9.1