From 4413d1eb47fa400277c8a9625aa0bd5c424a2fab Mon Sep 17 00:00:00 2001
From: zhaomingwork <61895407+zhaomingwork@users.noreply.github.com>
Date: 星期四, 06 七月 2023 10:13:32 +0800
Subject: [PATCH] Python ws client slow problem for multiple files in offline mode (#716)
---
funasr/runtime/python/websocket/funasr_wss_client.py | 26 +++++++++++++++++---------
1 files changed, 17 insertions(+), 9 deletions(-)
diff --git a/funasr/runtime/python/websocket/funasr_wss_client.py b/funasr/runtime/python/websocket/funasr_wss_client.py
index a3f5405..765addb 100644
--- a/funasr/runtime/python/websocket/funasr_wss_client.py
+++ b/funasr/runtime/python/websocket/funasr_wss_client.py
@@ -138,8 +138,17 @@
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 +177,9 @@
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":
@@ -287,9 +295,9 @@
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:
--
Gitblit v1.9.1