From fc08b62d05723cdc1ce021bb8ba044ca014fb1f7 Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期一, 13 三月 2023 18:38:41 +0800
Subject: [PATCH] readme
---
funasr/runtime/python/onnxruntime/rapid_paraformer/utils/timestamp_utils.py | 16 ++++++++--------
1 files changed, 8 insertions(+), 8 deletions(-)
diff --git a/funasr/runtime/python/onnxruntime/rapid_paraformer/utils/timestamp_utils.py b/funasr/runtime/python/onnxruntime/rapid_paraformer/utils/timestamp_utils.py
index 32dd849..dd702f3 100644
--- a/funasr/runtime/python/onnxruntime/rapid_paraformer/utils/timestamp_utils.py
+++ b/funasr/runtime/python/onnxruntime/rapid_paraformer/utils/timestamp_utils.py
@@ -1,15 +1,14 @@
import numpy as np
-def time_stamp_lfr6_onnx(us_cif_peak, char_list, begin_time=0.0):
+def time_stamp_lfr6_onnx(us_cif_peak, char_list, begin_time=0.0, total_offset=-1.5):
if not len(char_list):
return []
START_END_THRESHOLD = 5
- MAX_TOKEN_DURATION = 14
+ MAX_TOKEN_DURATION = 30
TIME_RATE = 10.0 * 6 / 1000 / 3 # 3 times upsampled
cif_peak = us_cif_peak.reshape(-1)
num_frames = cif_peak.shape[-1]
- import pdb; pdb.set_trace()
if char_list[-1] == '</s>':
char_list = char_list[:-1]
# char_list = [i for i in text]
@@ -17,7 +16,7 @@
new_char_list = []
# for bicif model trained with large data, cif2 actually fires when a character starts
# so treat the frames between two peaks as the duration of the former token
- fire_place = np.where(cif_peak>1.0-1e-4)[0] - 1.5 # np format
+ fire_place = np.where(cif_peak>1.0-1e-4)[0] + total_offset # np format
num_peak = len(fire_place)
assert num_peak == len(char_list) + 1 # number of peaks is supposed to be number of tokens + 1
# begin silence
@@ -28,7 +27,7 @@
# tokens timestamp
for i in range(len(fire_place)-1):
new_char_list.append(char_list[i])
- if MAX_TOKEN_DURATION < 0 or fire_place[i+1] - fire_place[i] < MAX_TOKEN_DURATION:
+ if i == len(fire_place)-2 or MAX_TOKEN_DURATION < 0 or fire_place[i+1] - fire_place[i] < MAX_TOKEN_DURATION:
timestamp_list.append([fire_place[i]*TIME_RATE, fire_place[i+1]*TIME_RATE])
else:
# cut the duration to token and sil of the 0-weight frames last long
@@ -49,11 +48,12 @@
timestamp_list[i][0] = timestamp_list[i][0] + begin_time / 1000.0
timestamp_list[i][1] = timestamp_list[i][1] + begin_time / 1000.0
assert len(new_char_list) == len(timestamp_list)
- res_txt = ""
+ res_total = []
for char, timestamp in zip(new_char_list, timestamp_list):
- res_txt += "{} {} {};".format(char, timestamp[0], timestamp[1])
+ res_total.append([char, timestamp[0], timestamp[1]]) # += "{} {} {};".format(char, timestamp[0], timestamp[1])
res = []
for char, timestamp in zip(new_char_list, timestamp_list):
if char != '<sil>':
res.append([int(timestamp[0] * 1000), int(timestamp[1] * 1000)])
- return res
\ No newline at end of file
+ return res, res_total
+
\ No newline at end of file
--
Gitblit v1.9.1