From b0f4910de6dc91c13828026fb5bdd4f15d8636f3 Mon Sep 17 00:00:00 2001
From: shixian.shi <shixian.shi@alibaba-inc.com>
Date: 星期二, 27 六月 2023 20:11:30 +0800
Subject: [PATCH] update
---
funasr/bin/asr_infer.py | 16 +++++++++++-----
1 files changed, 11 insertions(+), 5 deletions(-)
diff --git a/funasr/bin/asr_infer.py b/funasr/bin/asr_infer.py
index e12dbb5..0ce8dd8 100644
--- a/funasr/bin/asr_infer.py
+++ b/funasr/bin/asr_infer.py
@@ -285,6 +285,7 @@
nbest: int = 1,
frontend_conf: dict = None,
hotword_list_or_file: str = None,
+ clas_scale: float = 1.0,
decoding_ind: int = 0,
**kwargs,
):
@@ -382,6 +383,7 @@
# 6. [Optional] Build hotword list from str, local file or url
self.hotword_list = None
self.hotword_list = self.generate_hotwords_list(hotword_list_or_file)
+ self.clas_scale = clas_scale
is_use_lm = lm_weight != 0.0 and lm_file is not None
if (ctc_weight == 0.0 or asr_model.ctc == None) and not is_use_lm:
@@ -446,16 +448,20 @@
pre_token_length = pre_token_length.round().long()
if torch.max(pre_token_length) < 1:
return []
- if not isinstance(self.asr_model, ContextualParaformer) and not isinstance(self.asr_model,
- NeatContextualParaformer):
+ if not isinstance(self.asr_model, ContextualParaformer) and \
+ not isinstance(self.asr_model, NeatContextualParaformer):
if self.hotword_list:
logging.warning("Hotword is given but asr model is not a ContextualParaformer.")
decoder_outs = self.asr_model.cal_decoder_with_predictor(enc, enc_len, pre_acoustic_embeds,
pre_token_length)
decoder_out, ys_pad_lens = decoder_outs[0], decoder_outs[1]
else:
- decoder_outs = self.asr_model.cal_decoder_with_predictor(enc, enc_len, pre_acoustic_embeds,
- pre_token_length, hw_list=self.hotword_list)
+ decoder_outs = self.asr_model.cal_decoder_with_predictor(enc,
+ enc_len,
+ pre_acoustic_embeds,
+ pre_token_length,
+ hw_list=self.hotword_list,
+ clas_scale=self.clas_scale)
decoder_out, ys_pad_lens = decoder_outs[0], decoder_outs[1]
if isinstance(self.asr_model, BiCifParaformer):
@@ -609,7 +615,7 @@
hotword_str_list = []
for hw in hotword_list_or_file.strip().split():
hotword_str_list.append(hw)
- hw_list = hw
+ hw_list = hw.strip().split()
if seg_dict is not None:
hw_list = seg_tokenize(hw_list, seg_dict)
hotword_list.append(self.converter.tokens2ids(hw_list))
--
Gitblit v1.9.1