From 3eee773814c392e497557bbad501e0add4c8eca9 Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期日, 09 六月 2024 02:11:42 +0800
Subject: [PATCH] fix bug
---
funasr/datasets/audio_datasets/update_jsonl.py | 27 ++++++++++++++-------------
1 files changed, 14 insertions(+), 13 deletions(-)
diff --git a/funasr/datasets/audio_datasets/update_jsonl.py b/funasr/datasets/audio_datasets/update_jsonl.py
index 0a3e0ec..bc84708 100644
--- a/funasr/datasets/audio_datasets/update_jsonl.py
+++ b/funasr/datasets/audio_datasets/update_jsonl.py
@@ -31,7 +31,7 @@
else:
for i in range(num_total):
update_data(lines, i)
- print("All audio durations have been processed.")
+ logging.info("All audio durations have been processed.")
for line in lines:
@@ -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:
- print(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):
@@ -67,7 +68,7 @@
for i, jsonl in enumerate(data_file_lists):
filename_with_extension = os.path.basename(jsonl.strip())
jsonl_file_out = os.path.join(jsonl_file_out_dir, filename_with_extension)
- print(f"{i}/{len(data_file_lists)}, jsonl: {jsonl}, {jsonl_file_out}")
+ logging.info(f"{i}/{len(data_file_lists)}, jsonl: {jsonl}, {jsonl_file_out}")
gen_scp_from_jsonl(jsonl.strip(), jsonl_file_out, ncpu)
@@ -76,7 +77,7 @@
def main_hydra(cfg: DictConfig):
kwargs = OmegaConf.to_container(cfg, resolve=True)
- print(kwargs)
+ logging.info(kwargs)
jsonl_file_list_in = kwargs.get(
"jsonl_file_list_in", "/Users/zhifu/funasr1.0/data/list/data_jsonl.list"
--
Gitblit v1.9.1