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