From 12d8bd77a6686e29f6840e8de3909f3aaf96afa3 Mon Sep 17 00:00:00 2001
From: 语帆 <yf352572@alibaba-inc.com>
Date: 星期三, 28 二月 2024 16:48:11 +0800
Subject: [PATCH] test
---
funasr/models/lcbnet/model.py | 29 +++++++++++++++++------------
1 files changed, 17 insertions(+), 12 deletions(-)
diff --git a/funasr/models/lcbnet/model.py b/funasr/models/lcbnet/model.py
index 45b1ee5..82a1b78 100644
--- a/funasr/models/lcbnet/model.py
+++ b/funasr/models/lcbnet/model.py
@@ -111,8 +111,8 @@
)
self.blank_id = blank_id
- self.sos = sos if sos is not None else vocab_size - 1
- self.eos = eos if eos is not None else vocab_size - 1
+ self.sos = vocab_size - 1
+ self.eos = vocab_size - 1
self.vocab_size = vocab_size
self.ignore_id = ignore_id
self.ctc_weight = ctc_weight
@@ -274,15 +274,12 @@
ind: int
"""
with autocast(False):
- pdb.set_trace()
# Data augmentation
if self.specaug is not None and self.training:
speech, speech_lengths = self.specaug(speech, speech_lengths)
- pdb.set_trace()
# Normalization for feature: e.g. Global-CMVN, Utterance-CMVN
if self.normalize is not None:
speech, speech_lengths = self.normalize(speech, speech_lengths)
- pdb.set_trace()
# Forward encoder
# feats: (Batch, Length, Dim)
# -> encoder_out: (Batch, Length2, Dim2)
@@ -299,7 +296,6 @@
if intermediate_outs is not None:
return (encoder_out, intermediate_outs), encoder_out_lens
- pdb.set_trace()
return encoder_out, encoder_out_lens
def _calc_att_loss(
@@ -379,14 +375,14 @@
scorers["ngram"] = ngram
weights = dict(
- decoder=1.0 - kwargs.get("decoding_ctc_weight", 0.5),
- ctc=kwargs.get("decoding_ctc_weight", 0.5),
+ decoder=1.0 - kwargs.get("decoding_ctc_weight", 0.3),
+ ctc=kwargs.get("decoding_ctc_weight", 0.3),
lm=kwargs.get("lm_weight", 0.0),
ngram=kwargs.get("ngram_weight", 0.0),
length_bonus=kwargs.get("penalty", 0.0),
)
beam_search = BeamSearch(
- beam_size=kwargs.get("beam_size", 10),
+ beam_size=kwargs.get("beam_size", 20),
weights=weights,
scorers=scorers,
sos=self.sos,
@@ -442,12 +438,18 @@
speech = speech.to(device=kwargs["device"])
speech_lengths = speech_lengths.to(device=kwargs["device"])
- pdb.set_trace()
# Encoder
encoder_out, encoder_out_lens = self.encode(speech, speech_lengths)
if isinstance(encoder_out, tuple):
encoder_out = encoder_out[0]
+ ocr_list_new = [[x + 1 if x != 0 else x for x in sublist] for sublist in ocr_sample_list]
+ ocr = torch.tensor(ocr_list_new)
+ ocr_lengths = ocr.new_full([1], dtype=torch.long, fill_value=ocr.size(1))
+ ocr, ocr_lens, _ = self.text_encoder(ocr, ocr_lengths)
+ fusion_out, _, _, _ = self.fusion_encoder(encoder_out,None, ocr, None)
+ encoder_out = encoder_out + fusion_out
+ pdb.set_trace()
# c. Passed the encoder result and the beam search
nbest_hyps = self.beam_search(
x=encoder_out[0], maxlenratio=kwargs.get("maxlenratio", 0.0), minlenratio=kwargs.get("minlenratio", 0.0)
@@ -455,7 +457,7 @@
nbest_hyps = nbest_hyps[: self.nbest]
-
+ pdb.set_trace()
results = []
b, n, d = encoder_out.size()
for i in range(b):
@@ -477,10 +479,13 @@
# remove blank symbol id, which is assumed to be 0
token_int = list(filter(lambda x: x != self.eos and x != self.sos and x != self.blank_id, token_int))
+ pdb.set_trace()
# Change integer-ids to tokens
token = tokenizer.ids2tokens(token_int)
+ pdb.set_trace()
text = tokenizer.tokens2text(token)
-
+ pdb.set_trace()
+
text_postprocessed, _ = postprocess_utils.sentence_postprocess(token)
result_i = {"key": key[i], "token": token, "text": text_postprocessed}
results.append(result_i)
--
Gitblit v1.9.1