From 8912e0696af069de47646fdb8a9d9c4e086e88b3 Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期日, 14 一月 2024 23:42:11 +0800
Subject: [PATCH] Resolve merge conflict

---
 runtime/python/websocket/funasr_wss_client.py |   23 +++++++++++------------
 1 files changed, 11 insertions(+), 12 deletions(-)

diff --git a/runtime/python/websocket/funasr_wss_client.py b/runtime/python/websocket/funasr_wss_client.py
index 66b3ce0..92dc548 100644
--- a/runtime/python/websocket/funasr_wss_client.py
+++ b/runtime/python/websocket/funasr_wss_client.py
@@ -41,6 +41,10 @@
                     type=str,
                     default=None,
                     help="audio_in")
+parser.add_argument("--audio_fs",
+                    type=int,
+                    default=16000,
+                    help="audio_fs")
 parser.add_argument("--send_without_sleep",
                     action="store_true",
                     default=True,
@@ -164,7 +168,7 @@
         hotword_msg=json.dumps(fst_dict)
         print (hotword_msg)
 
-    sample_rate = 16000
+    sample_rate = args.audio_fs
     wav_format = "pcm"
     use_itn=True
     if args.use_itn == 0:
@@ -182,20 +186,12 @@
         if wav_path.endswith(".pcm"):
             with open(wav_path, "rb") as f:
                 audio_bytes = f.read()
-        elif wav_path.endswith(".wav"):
-            import wave
-            with wave.open(wav_path, "rb") as wav_file:
-                params = wav_file.getparams()
-                sample_rate = wav_file.getframerate()
-                frames = wav_file.readframes(wav_file.getnframes())
-                audio_bytes = bytes(frames)
         else:
             wav_format = "others"
             with open(wav_path, "rb") as f:
                 audio_bytes = f.read()
 
-        # stride = int(args.chunk_size/1000*16000*2)
-        stride = int(60 * args.chunk_size[1] / args.chunk_interval / 1000 * 16000 * 2)
+        stride = int(60 * args.chunk_size[1] / args.chunk_interval / 1000 * sample_rate * 2)
         chunk_num = (len(audio_bytes) - 1) // stride + 1
         # print(stride)
 
@@ -253,6 +249,7 @@
             wav_name = meg.get("wav_name", "demo")
             text = meg["text"]
             timestamp=""
+            offline_msg_done = meg.get("is_final", False)
             if "timestamp" in meg:
                 timestamp = meg["timestamp"]
 
@@ -262,7 +259,9 @@
                 else:
                     text_write_line = "{}\t{}\n".format(wav_name, text)
                 ibest_writer.write(text_write_line)
-                
+
+            if 'mode' not in meg:
+                continue
             if meg["mode"] == "online":
                 text_print += "{}".format(text)
                 text_print = text_print[-args.words_max_print:]
@@ -289,7 +288,7 @@
                 text_print = text_print[-args.words_max_print:]
                 os.system('clear')
                 print("\rpid" + str(id) + ": " + text_print)
-                offline_msg_done=True
+                # offline_msg_done=True
 
     except Exception as e:
             print("Exception:", e)

--
Gitblit v1.9.1