From 40eefbe376bd2e846bd9c451636f4e42ba1bf8bf Mon Sep 17 00:00:00 2001
From: zhuzizyf <42790740+zhuzizyf@users.noreply.github.com>
Date: 星期三, 12 四月 2023 17:18:19 +0800
Subject: [PATCH] Merge pull request #1 from zhuzizyf/fix-dataset-bug
---
funasr/bin/asr_inference_paraformer_vad_punc.py | 10 ++++++----
1 files changed, 6 insertions(+), 4 deletions(-)
diff --git a/funasr/bin/asr_inference_paraformer_vad_punc.py b/funasr/bin/asr_inference_paraformer_vad_punc.py
index 1dc98f6..9dc0b79 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))
@@ -668,7 +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