From 94de39dde2e616a01683c518023d0fab72b4e103 Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期一, 19 二月 2024 22:21:50 +0800
Subject: [PATCH] aishell example
---
funasr/utils/timestamp_tools.py | 120 +++++++++++++++++++++++++++++++++++++++---------------------
1 files changed, 78 insertions(+), 42 deletions(-)
diff --git a/funasr/utils/timestamp_tools.py b/funasr/utils/timestamp_tools.py
index f8adbbc..63f179a 100644
--- a/funasr/utils/timestamp_tools.py
+++ b/funasr/utils/timestamp_tools.py
@@ -1,36 +1,61 @@
import torch
-import copy
+import codecs
import logging
+import argparse
import numpy as np
-from typing import Any, List, Tuple, Union
+# import edit_distance
+from itertools import zip_longest
+
+
+def cif_wo_hidden(alphas, threshold):
+ batch_size, len_time = alphas.size()
+ # loop varss
+ integrate = torch.zeros([batch_size], device=alphas.device)
+ # intermediate vars along time
+ list_fires = []
+ for t in range(len_time):
+ alpha = alphas[:, t]
+ integrate += alpha
+ list_fires.append(integrate)
+ fire_place = integrate >= threshold
+ integrate = torch.where(fire_place,
+ integrate - torch.ones([batch_size], device=alphas.device)*threshold,
+ integrate)
+ fires = torch.stack(list_fires, 1)
+ return fires
def ts_prediction_lfr6_standard(us_alphas,
- us_cif_peak,
+ us_peaks,
char_list,
vad_offset=0.0,
- end_time=None,
- 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
if len(us_alphas.shape) == 2:
- alphas, cif_peak = us_alphas[0], us_cif_peak[0] # support inference batch_size=1 only
+ alphas, peaks = us_alphas[0], us_peaks[0] # support inference batch_size=1 only
else:
- alphas, cif_peak = us_alphas, us_cif_peak
- num_frames = cif_peak.shape[0]
+ alphas, peaks = us_alphas, us_peaks
if char_list[-1] == '</s>':
char_list = char_list[:-1]
+ fire_place = torch.where(peaks>1.0-1e-4)[0].cpu().numpy() + force_time_shift # total offset
+ if len(fire_place) != len(char_list) + 1:
+ alphas /= (alphas.sum() / (len(char_list) + 1))
+ alphas = alphas.unsqueeze(0)
+ peaks = cif_wo_hidden(alphas, threshold=1.0-1e-4)[0]
+ fire_place = torch.where(peaks>1.0-1e-4)[0].cpu().numpy() + force_time_shift # total offset
+ num_frames = peaks.shape[0]
timestamp_list = []
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 = torch.where(cif_peak>1.0-1e-4)[0].cpu().numpy() + force_time_shift # total offset
- num_peak = len(fire_place)
- assert num_peak == len(char_list) + 1 # number of peaks is supposed to be number of tokens + 1
+ fire_place = torch.where(peaks>1.0-1e-4)[0].cpu().numpy() + force_time_shift # total offset
+ # assert num_peak == len(char_list) + 1 # number of peaks is supposed to be number of tokens + 1
# begin silence
if fire_place[0] > START_END_THRESHOLD:
# char_list.insert(0, '<sil>')
@@ -63,6 +88,8 @@
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):
@@ -71,54 +98,63 @@
return res_txt, res
-def time_stamp_sentence(punc_id_list, time_stamp_postprocessed, text_postprocessed):
+def timestamp_sentence(punc_id_list, timestamp_postprocessed, text_postprocessed):
+ punc_list = ['锛�', '銆�', '锛�', '銆�']
res = []
if text_postprocessed is None:
return res
- if time_stamp_postprocessed is None:
+ if timestamp_postprocessed is None:
return res
- if len(time_stamp_postprocessed) == 0:
+ if len(timestamp_postprocessed) == 0:
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(),
- "start": time_stamp_postprocessed[0][0],
- "end": time_stamp_postprocessed[-1][1]
+ "start": timestamp_postprocessed[0][0],
+ "end": timestamp_postprocessed[-1][1],
+ "timestamp": timestamp_postprocessed,
})
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
-
- sentence_text = ''
- sentence_start = time_stamp_postprocessed[0][0]
+ if len(punc_id_list) != len(timestamp_postprocessed):
+ logging.warning("length mismatch between punc and timestamp")
+ sentence_text = ""
+ sentence_text_seg = ""
+ ts_list = []
+ sentence_start = timestamp_postprocessed[0][0]
+ sentence_end = timestamp_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:
- sentence_text += ','
+ punc_stamp_text_list = list(zip_longest(punc_id_list, timestamp_postprocessed, texts, fillvalue=None))
+ for punc_stamp_text in punc_stamp_text_list:
+ punc_id, timestamp, text = punc_stamp_text
+ # sentence_text += text if text is not None else ''
+ if text is not None:
+ if 'a' <= text[0] <= 'z' or 'A' <= text[0] <= 'Z':
+ sentence_text += ' ' + text
+ elif len(sentence_text) and ('a' <= sentence_text[-1] <= 'z' or 'A' <= sentence_text[-1] <= 'Z'):
+ sentence_text += ' ' + text
+ else:
+ sentence_text += text
+ sentence_text_seg += text + ' '
+ ts_list.append(timestamp)
+
+ punc_id = int(punc_id) if punc_id is not None else 1
+ sentence_end = timestamp[1] if timestamp is not None else sentence_end
+
+ if punc_id > 1:
+ sentence_text += punc_list[punc_id - 2]
res.append({
'text': sentence_text,
"start": sentence_start,
- "end": time_stamp_postprocessed[i][1]
+ "end": sentence_end,
+ "timestamp": ts_list
})
sentence_text = ''
- sentence_start = time_stamp_postprocessed[i][1]
- elif punc_id_list[i] == 3:
- sentence_text += '.'
- res.append({
- 'text': sentence_text,
- "start": sentence_start,
- "end": time_stamp_postprocessed[i][1]
- })
- sentence_text = ''
- sentence_start = time_stamp_postprocessed[i][1]
+ sentence_text_seg = ''
+ ts_list = []
+ sentence_start = sentence_end
return res
--
Gitblit v1.9.1