From c2e4e3c2e9be855277d9f4fa9cd0544892ff829a Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期三, 30 八月 2023 09:57:30 +0800
Subject: [PATCH] Merge branch 'main' of github.com:alibaba-damo-academy/FunASR add
---
funasr/runtime/python/websocket/funasr_wss_client.py | 38 ++++++++++++++++++++++++--------------
1 files changed, 24 insertions(+), 14 deletions(-)
diff --git a/funasr/runtime/python/websocket/funasr_wss_client.py b/funasr/runtime/python/websocket/funasr_wss_client.py
index a3f5405..bed0081 100644
--- a/funasr/runtime/python/websocket/funasr_wss_client.py
+++ b/funasr/runtime/python/websocket/funasr_wss_client.py
@@ -12,7 +12,6 @@
import logging
-SUPPORT_AUDIO_TYPE_SETS = ['.wav', '.pcm']
logging.basicConfig(level=logging.ERROR)
parser = argparse.ArgumentParser()
@@ -138,8 +137,17 @@
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)
@@ -168,10 +176,9 @@
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":
@@ -189,7 +196,7 @@
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)), "w+", encoding="utf-8")
+ ibest_writer = open(os.path.join(args.output_dir, "text.{}".format(id)), "a", encoding="utf-8")
else:
ibest_writer = None
try:
@@ -197,6 +204,7 @@
meg = await websocket.recv()
meg = json.loads(meg)
+ # print(meg)
wav_name = meg.get("wav_name", "demo")
text = meg["text"]
@@ -211,10 +219,14 @@
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)
@@ -287,9 +299,7 @@
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