From 00d0df3a1018c63ec8c5d13e611f53c564c0a7e2 Mon Sep 17 00:00:00 2001
From: zhifu gao <zhifu.gzf@alibaba-inc.com>
Date: 星期一, 06 五月 2024 22:17:25 +0800
Subject: [PATCH] Dev gzf decoding (#1695)
---
funasr/datasets/audio_datasets/update_jsonl.py | 21 +++++++++++----------
1 files changed, 11 insertions(+), 10 deletions(-)
diff --git a/funasr/datasets/audio_datasets/update_jsonl.py b/funasr/datasets/audio_datasets/update_jsonl.py
index 05870fe..bc84708 100644
--- a/funasr/datasets/audio_datasets/update_jsonl.py
+++ b/funasr/datasets/audio_datasets/update_jsonl.py
@@ -46,16 +46,17 @@
data = json.loads(line.strip())
wav_path = data["source"].replace("/cpfs01", "/cpfs_speech/data")
- waveform, _ = librosa.load(wav_path, sr=16000)
- sample_num = len(waveform)
- source_len = int(sample_num / 16000 * 1000 / 10)
- source_len_old = data["source_len"]
- # if (source_len_old - source_len) > 100 or (source_len - source_len_old) > 100:
- # logging.info(f"old: {source_len_old}, new: {source_len}, wav: {wav_path}")
- data["source_len"] = source_len
- data["source"] = wav_path
- jsonl_line = json.dumps(data, ensure_ascii=False)
- lines[i] = jsonl_line
+ if os.path.exists(wav_path):
+ waveform, _ = librosa.load(wav_path, sr=16000)
+ sample_num = len(waveform)
+ source_len = int(sample_num / 16000 * 1000 / 10)
+ source_len_old = data["source_len"]
+ # if (source_len_old - source_len) > 100 or (source_len - source_len_old) > 100:
+ # logging.info(f"old: {source_len_old}, new: {source_len}, wav: {wav_path}")
+ data["source_len"] = source_len
+ data["source"] = wav_path
+ jsonl_line = json.dumps(data, ensure_ascii=False)
+ lines[i] = jsonl_line
def update_wav_len(jsonl_file_list_in, jsonl_file_out_dir, ncpu=1):
--
Gitblit v1.9.1