From 1596f6f414f6f41da66506debb1dff19fffeb3ec Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期一, 24 六月 2024 11:55:17 +0800
Subject: [PATCH] fixbug hotwords
---
funasr/datasets/large_datasets/utils/filter.py | 21 +++++++++++----------
1 files changed, 11 insertions(+), 10 deletions(-)
diff --git a/funasr/datasets/large_datasets/utils/filter.py b/funasr/datasets/large_datasets/utils/filter.py
index 1260a47..adc8fa0 100644
--- a/funasr/datasets/large_datasets/utils/filter.py
+++ b/funasr/datasets/large_datasets/utils/filter.py
@@ -1,26 +1,27 @@
#!/usr/bin/env python
-def filter(data,
- speech_length_min=100,
- speech_length_max=15000,
- token_length_min=0,
- token_length_max=200):
+def filter(
+ data, speech_length_min=100, speech_length_max=15000, token_length_min=0, token_length_max=200
+):
assert "speech" in data or "text" in data
if "speech" in data and "text" in data:
if "sampling_rate" in data:
- speech_length = (data["speech"].shape[0] / data["sampling_rate"]) * 1000.
+ speech_length = (data["speech"].shape[0] / data["sampling_rate"]) * 1000.0
else:
speech_length = data["speech"].shape[0]
- num_tokens = len(data['text'])
- return speech_length_min < speech_length < speech_length_max and token_length_min < num_tokens < token_length_max
+ num_tokens = len(data["text"])
+ return (
+ speech_length_min < speech_length < speech_length_max
+ and token_length_min < num_tokens < token_length_max
+ )
elif "speech" in data:
if "sampling_rate" in data:
- speech_length = (data["speech"].shape[0] / data["sampling_rate"]) * 1000.
+ speech_length = (data["speech"].shape[0] / data["sampling_rate"]) * 1000.0
else:
speech_length = data["speech"].shape[0]
return speech_length_min < speech_length < speech_length_max
else:
- num_tokens = len(data['text'])
+ num_tokens = len(data["text"])
return token_length_min < num_tokens < token_length_max
--
Gitblit v1.9.1