From 111450d5e67ed01e3e7de088fe5bb3115dc7eeff Mon Sep 17 00:00:00 2001
From: mengzhe.cmz <mengzhe.cmz@alibaba-inc.com>
Date: 星期四, 23 三月 2023 19:55:15 +0800
Subject: [PATCH] update infer.py
---
funasr/bin/asr_inference_paraformer_vad_punc.py | 8 +++++---
1 files changed, 5 insertions(+), 3 deletions(-)
diff --git a/funasr/bin/asr_inference_paraformer_vad_punc.py b/funasr/bin/asr_inference_paraformer_vad_punc.py
index 1dc98f6..ab3e1e3 100644
--- a/funasr/bin/asr_inference_paraformer_vad_punc.py
+++ b/funasr/bin/asr_inference_paraformer_vad_punc.py
@@ -58,7 +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), ...]
@@ -256,7 +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 = []
@@ -292,6 +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 +305,7 @@
if isinstance(self.asr_model, BiCifParaformer):
_, timestamp = ts_prediction_lfr6_standard(us_alphas[i],
- us_cif_peak[i],
+ us_peaks[i],
copy.copy(token),
vad_offset=begin_time)
results.append((text, token, token_int, timestamp, enc_len_batch_total, lfr_factor))
--
Gitblit v1.9.1