From 6427c834dfd97b1f05c6659cdc7ccf010bf82fe1 Mon Sep 17 00:00:00 2001
From: 嘉渊 <wangjiaming.wjm@alibaba-inc.com>
Date: 星期一, 24 四月 2023 19:50:07 +0800
Subject: [PATCH] update
---
funasr/utils/timestamp_tools.py | 101 +++++++++++++++++++++++++++++++++++++++-----------
1 files changed, 79 insertions(+), 22 deletions(-)
diff --git a/funasr/utils/timestamp_tools.py b/funasr/utils/timestamp_tools.py
index 73f0c7a..87cc49e 100644
--- a/funasr/utils/timestamp_tools.py
+++ b/funasr/utils/timestamp_tools.py
@@ -1,10 +1,12 @@
-from scipy.fftpack import shift
+from itertools import zip_longest
+
import torch
import copy
import codecs
import logging
import edit_distance
import argparse
+import pdb
import numpy as np
from typing import Any, List, Tuple, Union
@@ -13,10 +15,11 @@
us_peaks,
char_list,
vad_offset=0.0,
- force_time_shift=-1.5
+ force_time_shift=-1.5,
+ sil_in_str=True
):
if not len(char_list):
- return []
+ return "", []
START_END_THRESHOLD = 5
MAX_TOKEN_DURATION = 12
TIME_RATE = 10.0 * 6 / 1000 / 3 # 3 times upsampled
@@ -66,6 +69,8 @@
timestamp_list[i][1] = timestamp_list[i][1] + vad_offset / 1000.0
res_txt = ""
for char, timestamp in zip(new_char_list, timestamp_list):
+ #if char != '<sil>':
+ if not sil_in_str and char == '<sil>': continue
res_txt += "{} {} {};".format(char, str(timestamp[0]+0.0005)[:5], str(timestamp[1]+0.0005)[:5])
res = []
for char, timestamp in zip(new_char_list, timestamp_list):
@@ -84,6 +89,7 @@
return res
if len(text_postprocessed) == 0:
return res
+
if punc_id_list is None or len(punc_id_list) == 0:
res.append({
'text': text_postprocessed.split(),
@@ -92,36 +98,45 @@
})
return res
if len(punc_id_list) != len(time_stamp_postprocessed):
- res.append({
- 'text': text_postprocessed.split(),
- "start": time_stamp_postprocessed[0][0],
- "end": time_stamp_postprocessed[-1][1]
- })
- return res
-
+ print(" warning length mistach!!!!!!")
sentence_text = ''
sentence_start = time_stamp_postprocessed[0][0]
+ sentence_end = time_stamp_postprocessed[0][1]
texts = text_postprocessed.split()
- for i in range(len(punc_id_list)):
- sentence_text += texts[i]
- if punc_id_list[i] == 2:
+ punc_stamp_text_list = list(zip_longest(punc_id_list, time_stamp_postprocessed, texts, fillvalue=None))
+ for punc_stamp_text in punc_stamp_text_list:
+ punc_id, time_stamp, text = punc_stamp_text
+ sentence_text += text if text is not None else ''
+ punc_id = int(punc_id) if punc_id is not None else 1
+ sentence_end = time_stamp[1] if time_stamp is not None else sentence_end
+
+ if punc_id == 2:
sentence_text += ','
res.append({
'text': sentence_text,
"start": sentence_start,
- "end": time_stamp_postprocessed[i][1]
+ "end": sentence_end
})
sentence_text = ''
- sentence_start = time_stamp_postprocessed[i][1]
- elif punc_id_list[i] == 3:
+ sentence_start = sentence_end
+ elif punc_id == 3:
sentence_text += '.'
res.append({
'text': sentence_text,
"start": sentence_start,
- "end": time_stamp_postprocessed[i][1]
+ "end": sentence_end
})
sentence_text = ''
- sentence_start = time_stamp_postprocessed[i][1]
+ sentence_start = sentence_end
+ elif punc_id == 4:
+ sentence_text += '?'
+ res.append({
+ 'text': sentence_text,
+ "start": sentence_start,
+ "end": sentence_end
+ })
+ sentence_text = ''
+ sentence_start = sentence_end
return res
@@ -134,9 +149,9 @@
uttid_intersection = self._intersection(uttid_list1, uttid_list2)
res = self.as_cal(uttid_intersection, ts_dict1, ts_dict2)
logging.warning("Average shift of {} and {}: {}.".format(file1, file2, str(res)[:8]))
- logging.warning("Following timestamp pair differs most: {}, detail:{}".format(self.max_shift_uttid))
+ logging.warning("Following timestamp pair differs most: {}, detail:{}".format(self.max_shift, self.max_shift_uttid))
- def _intersection(list1, list2):
+ def _intersection(self, list1, list2):
set1 = set(list1)
set2 = set(list2)
if set1 == set2:
@@ -170,8 +185,9 @@
return uttid_list, ts_dict
def _shift(self, filtered_timestamp_list1, filtered_timestamp_list2):
+ shift_time = 0
for fts1, fts2 in zip(filtered_timestamp_list1, filtered_timestamp_list2):
- shift_time = abs(fts1[0] - fts2[0]) + abs(fts1[1] - fts2[1])
+ shift_time += abs(fts1[0] - fts2[0]) + abs(fts1[1] - fts2[1])
num_tokens = len(filtered_timestamp_list1)
return shift_time, num_tokens
@@ -232,13 +248,54 @@
return self._accumlated_shift / self._accumlated_tokens
-SUPPORTED_MODES = ['cal_aas']
+def convert_external_alphas(alphas_file, text_file, output_file):
+ from funasr.models.predictor.cif import cif_wo_hidden
+ with open(alphas_file, 'r') as f1, open(text_file, 'r') as f2, open(output_file, 'w') as f3:
+ for line1, line2 in zip(f1.readlines(), f2.readlines()):
+ line1 = line1.rstrip()
+ line2 = line2.rstrip()
+ assert line1.split()[0] == line2.split()[0]
+ uttid = line1.split()[0]
+ alphas = [float(i) for i in line1.split()[1:]]
+ new_alphas = np.array(remove_chunk_padding(alphas))
+ new_alphas[-1] += 1e-4
+ text = line2.split()[1:]
+ if len(text) + 1 != int(new_alphas.sum()):
+ # force resize
+ new_alphas *= (len(text) + 1) / int(new_alphas.sum())
+ peaks = cif_wo_hidden(torch.Tensor(new_alphas).unsqueeze(0), 1.0-1e-4)
+ if " " in text:
+ text = text.split()
+ else:
+ text = [i for i in text]
+ res_str, _ = ts_prediction_lfr6_standard(new_alphas, peaks[0], text,
+ force_time_shift=-7.0,
+ sil_in_str=False)
+ f3.write("{} {}\n".format(uttid, res_str))
+
+
+def remove_chunk_padding(alphas):
+ # remove the padding part in alphas if using chunk paraformer for GPU
+ START_ZERO = 45
+ MID_ZERO = 75
+ REAL_FRAMES = 360 # for chunk based encoder 10-120-10 and fsmn padding 5
+ alphas = alphas[START_ZERO:] # remove the padding at beginning
+ new_alphas = []
+ while True:
+ new_alphas = new_alphas + alphas[:REAL_FRAMES]
+ alphas = alphas[REAL_FRAMES+MID_ZERO:]
+ if len(alphas) < REAL_FRAMES: break
+ return new_alphas
+
+SUPPORTED_MODES = ['cal_aas', 'read_ext_alphas']
def main(args):
if args.mode == 'cal_aas':
asc = AverageShiftCalculator()
asc(args.input, args.input2)
+ elif args.mode == 'read_ext_alphas':
+ convert_external_alphas(args.input, args.input2, args.output)
else:
logging.error("Mode {} not in SUPPORTED_MODES: {}.".format(args.mode, SUPPORTED_MODES))
--
Gitblit v1.9.1