From f62d6314b93416b301ca7bb0b62ccf9c4e6933e2 Mon Sep 17 00:00:00 2001
From: 嘉渊 <wangjiaming.wjm@alibaba-inc.com>
Date: 星期二, 11 七月 2023 00:52:21 +0800
Subject: [PATCH] update
---
funasr/runtime/python/websocket/funasr_wss_client.py | 56 +++++++++++++++++++++++++++++++-------------------------
1 files changed, 31 insertions(+), 25 deletions(-)
diff --git a/funasr/runtime/python/websocket/funasr_wss_client.py b/funasr/runtime/python/websocket/funasr_wss_client.py
index fc4d516..fad12ce 100644
--- a/funasr/runtime/python/websocket/funasr_wss_client.py
+++ b/funasr/runtime/python/websocket/funasr_wss_client.py
@@ -8,7 +8,7 @@
import json
import traceback
from multiprocessing import Process
-from funasr.fileio.datadir_writer import DatadirWriter
+# from funasr.fileio.datadir_writer import DatadirWriter
import logging
@@ -72,11 +72,13 @@
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():
@@ -136,8 +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)
@@ -186,6 +197,10 @@
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)), "w+", encoding="utf-8")
+ else:
+ ibest_writer = None
try:
while True:
@@ -193,13 +208,15 @@
meg = json.loads(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)
@@ -216,7 +233,7 @@
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 +244,6 @@
-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 +296,9 @@
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