From 24f73665e2d8ea8e4de2fe4f900bc539d7f7b989 Mon Sep 17 00:00:00 2001
From: hnluo <haoneng.lhn@alibaba-inc.com>
Date: 星期一, 17 四月 2023 15:49:45 +0800
Subject: [PATCH] Merge pull request #367 from alibaba-damo-academy/dev_lhn2
---
funasr/bin/asr_inference_paraformer_vad_punc.py | 16 ++++++++++------
1 files changed, 10 insertions(+), 6 deletions(-)
diff --git a/funasr/bin/asr_inference_paraformer_vad_punc.py b/funasr/bin/asr_inference_paraformer_vad_punc.py
index 1320877..9dc0b79 100644
--- a/funasr/bin/asr_inference_paraformer_vad_punc.py
+++ b/funasr/bin/asr_inference_paraformer_vad_punc.py
@@ -44,11 +44,10 @@
from funasr.models.frontend.wav_frontend import WavFrontend
from funasr.tasks.vad import VADTask
from funasr.bin.vad_inference import Speech2VadSegment
-from funasr.utils.timestamp_tools import time_stamp_lfr6_pl
+from funasr.utils.timestamp_tools import time_stamp_sentence, ts_prediction_lfr6_standard
from funasr.bin.punctuation_infer import Text2Punc
from funasr.models.e2e_asr_paraformer import BiCifParaformer, ContextualParaformer
-from funasr.utils.timestamp_tools import time_stamp_sentence
header_colors = '\033[95m'
end_colors = '\033[0m'
@@ -59,7 +58,7 @@
Examples:
>>> import soundfile
- >>> speech2text = Speech2Text("asr_config.yml", "asr.pth")
+ >>> speech2text = Speech2Text("asr_config.yml", "asr.pb")
>>> audio, rate = soundfile.read("speech.wav")
>>> speech2text(audio)
[(text, token, token_int, hypothesis object), ...]
@@ -257,7 +256,7 @@
decoder_out, ys_pad_lens = decoder_outs[0], decoder_outs[1]
if isinstance(self.asr_model, BiCifParaformer):
- _, _, us_alphas, us_cif_peak = self.asr_model.calc_predictor_timestamp(enc, enc_len,
+ _, _, us_alphas, us_peaks = self.asr_model.calc_predictor_timestamp(enc, enc_len,
pre_token_length) # test no bias cif2
results = []
@@ -293,6 +292,8 @@
# remove blank symbol id, which is assumed to be 0
token_int = list(filter(lambda x: x != 0 and x != 2, token_int))
+ if len(token_int) == 0:
+ continue
# Change integer-ids to tokens
token = self.converter.ids2tokens(token_int)
@@ -303,7 +304,10 @@
text = None
if isinstance(self.asr_model, BiCifParaformer):
- timestamp = time_stamp_lfr6_pl(us_alphas[i], us_cif_peak[i], copy.copy(token), begin_time, end_time)
+ _, timestamp = ts_prediction_lfr6_standard(us_alphas[i],
+ us_peaks[i],
+ copy.copy(token),
+ vad_offset=begin_time)
results.append((text, token, token_int, timestamp, enc_len_batch_total, lfr_factor))
else:
results.append((text, token, token_int, enc_len_batch_total, lfr_factor))
@@ -666,7 +670,7 @@
ibest_writer["token"][key] = " ".join(token)
ibest_writer["token_int"][key] = " ".join(map(str, token_int))
ibest_writer["vad"][key] = "{}".format(vadsegments)
- ibest_writer["text"][key] = text_postprocessed
+ ibest_writer["text"][key] = " ".join(word_lists)
ibest_writer["text_with_punc"][key] = text_postprocessed_punc
if time_stamp_postprocessed is not None:
ibest_writer["time_stamp"][key] = "{}".format(time_stamp_postprocessed)
--
Gitblit v1.9.1