From d836e403ada705b798f39442398ba74e7d2d2683 Mon Sep 17 00:00:00 2001
From: dyyzhmm <dyyzhmm@163.com>
Date: 星期三, 15 三月 2023 10:12:36 +0800
Subject: [PATCH] Merge pull request #2 from alibaba-damo-academy/main
---
funasr/bin/asr_inference_paraformer.py | 9 ++++++---
1 files changed, 6 insertions(+), 3 deletions(-)
diff --git a/funasr/bin/asr_inference_paraformer.py b/funasr/bin/asr_inference_paraformer.py
index 8265fc5..6413d92 100644
--- a/funasr/bin/asr_inference_paraformer.py
+++ b/funasr/bin/asr_inference_paraformer.py
@@ -42,7 +42,7 @@
from funasr.models.frontend.wav_frontend import WavFrontend
from funasr.models.e2e_asr_paraformer import BiCifParaformer, ContextualParaformer
from funasr.export.models.e2e_asr_paraformer import Paraformer as Paraformer_export
-from funasr.utils.timestamp_tools import time_stamp_lfr6_pl, time_stamp_sentence
+from funasr.utils.timestamp_tools import ts_prediction_lfr6_standard
class Speech2Text:
@@ -245,7 +245,7 @@
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 = []
@@ -291,7 +291,10 @@
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, hyp, timestamp, enc_len_batch_total, lfr_factor))
else:
results.append((text, token, token_int, hyp, enc_len_batch_total, lfr_factor))
--
Gitblit v1.9.1