From 2196844d1d6e5b8732c95896bb46f0eacdd9cf9d Mon Sep 17 00:00:00 2001
From: zhifu gao <zhifu.gzf@alibaba-inc.com>
Date: 星期三, 25 九月 2024 15:10:50 +0800
Subject: [PATCH] Dev kws (#2105)

---
 funasr/datasets/audio_datasets/scp2jsonl.py |   15 ++++++++++-----
 1 files changed, 10 insertions(+), 5 deletions(-)

diff --git a/funasr/datasets/audio_datasets/scp2jsonl.py b/funasr/datasets/audio_datasets/scp2jsonl.py
index f4c9d74..48c64d2 100644
--- a/funasr/datasets/audio_datasets/scp2jsonl.py
+++ b/funasr/datasets/audio_datasets/scp2jsonl.py
@@ -58,7 +58,8 @@
             for key in json_dict[data_type_list[0]].keys():
                 jsonl_line = {"key": key}
                 for data_file in data_type_list:
-                    jsonl_line.update(json_dict[data_file][key])
+                    if key in json_dict[data_file]:
+                        jsonl_line.update(json_dict[data_file][key])
                 jsonl_line = json.dumps(jsonl_line, ensure_ascii=False)
                 f.write(jsonl_line + "\n")
                 f.flush()
@@ -81,10 +82,14 @@
         key = lines[0]
         line = lines[1] if len(lines) > 1 else ""
         line = line.strip()
-        if os.path.exists(line):
-            waveform, _ = librosa.load(line, sr=16000)
-            sample_num = len(waveform)
-            context_len = int(sample_num / 16000 * 1000 / 10)
+        if data_type == "source":
+            if os.path.exists(line):
+                waveform, _ = librosa.load(line, sr=16000)
+                sample_num = len(waveform)
+                context_len = int(sample_num * 1000 / 16000 / 10)
+            else:
+                print("source file not found: {}".format(line))
+                continue
         else:
             context_len = len(line.split()) if " " in line else len(line)
         res[key] = {data_type: line, f"{data_type}_len": context_len}

--
Gitblit v1.9.1