From 602fe75a1f0a8d64ccb6fc4d69ad510872fdfd13 Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期五, 17 三月 2023 20:30:40 +0800
Subject: [PATCH] rtf benchmark
---
funasr/bin/asr_inference_paraformer_vad_punc.py | 6 +++---
1 files changed, 3 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..3f57751 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 = []
@@ -303,7 +303,7 @@
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