From 2cbebbb33435dc490b6a092f2e5903c7f0e3e33c Mon Sep 17 00:00:00 2001
From: zhifu gao <zhifu.gzf@alibaba-inc.com>
Date: 星期二, 31 一月 2023 17:54:02 +0800
Subject: [PATCH] Merge pull request #52 from alibaba-damo-academy/dev
---
funasr/bin/asr_inference_paraformer.py | 8 +++++---
1 files changed, 5 insertions(+), 3 deletions(-)
diff --git a/funasr/bin/asr_inference_paraformer.py b/funasr/bin/asr_inference_paraformer.py
index a50e038..cb140eb 100644
--- a/funasr/bin/asr_inference_paraformer.py
+++ b/funasr/bin/asr_inference_paraformer.py
@@ -169,7 +169,7 @@
self.converter = converter
self.tokenizer = tokenizer
is_use_lm = lm_weight != 0.0 and lm_file is not None
- if ctc_weight == 0.0 and not is_use_lm:
+ if (ctc_weight == 0.0 or asr_model.ctc == None) and not is_use_lm:
beam_search = None
self.beam_search = beam_search
logging.info(f"Beam_search: {self.beam_search}")
@@ -227,6 +227,8 @@
pre_acoustic_embeds, pre_token_length, alphas, pre_peak_index = predictor_outs[0], predictor_outs[1], \
predictor_outs[2], predictor_outs[3]
pre_token_length = pre_token_length.round().long()
+ if torch.max(pre_token_length) < 1:
+ return []
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]
@@ -394,7 +396,7 @@
# results = speech2text(**batch)
# if len(results) < 1:
# hyp = Hypothesis(score=0.0, scores={}, states={}, yseq=[])
-# results = [[" ", ["<space>"], [2], hyp, 10, 6]] * nbest
+# results = [[" ", ["sil"], [2], hyp, 10, 6]] * nbest
# time_end = time.time()
# forward_time = time_end - time_beg
# lfr_factor = results[0][-1]
@@ -621,7 +623,7 @@
results = speech2text(**batch)
if len(results) < 1:
hyp = Hypothesis(score=0.0, scores={}, states={}, yseq=[])
- results = [[" ", ["<space>"], [2], hyp, 10, 6]] * nbest
+ results = [[" ", ["sil"], [2], hyp, 10, 6]] * nbest
time_end = time.time()
forward_time = time_end - time_beg
lfr_factor = results[0][-1]
--
Gitblit v1.9.1