From 1d1ef01b4e23630a99a3be7e9d1dce9550a793e9 Mon Sep 17 00:00:00 2001
From: yhliang <68215459+yhliang-aslp@users.noreply.github.com>
Date: 星期四, 11 五月 2023 16:26:24 +0800
Subject: [PATCH] Merge branch 'main' into dev_smohan
---
funasr/datasets/large_datasets/dataset.py | 37 ++++++++++++++++++++++++++++++++++---
1 files changed, 34 insertions(+), 3 deletions(-)
diff --git a/funasr/datasets/large_datasets/dataset.py b/funasr/datasets/large_datasets/dataset.py
index b0e1b8f..8c224d8 100644
--- a/funasr/datasets/large_datasets/dataset.py
+++ b/funasr/datasets/large_datasets/dataset.py
@@ -101,7 +101,7 @@
if data_type == "kaldi_ark":
ark_reader = ReadHelper('ark:{}'.format(data_file))
reader_list.append(ark_reader)
- elif data_type == "text" or data_type == "sound":
+ elif data_type == "text" or data_type == "sound" or data_type == 'text_hotword':
text_reader = open(data_file, "r")
reader_list.append(text_reader)
elif data_type == "none":
@@ -131,6 +131,13 @@
sample_dict["sampling_rate"] = sampling_rate
if data_name == "speech":
sample_dict["key"] = key
+ elif data_type == "text_hotword":
+ text = item
+ segs = text.strip().split()
+ sample_dict[data_name] = segs[1:]
+ if "key" not in sample_dict:
+ sample_dict["key"] = segs[0]
+ sample_dict['hw_tag'] = 1
else:
text = item
segs = text.strip().split()
@@ -167,14 +174,38 @@
shuffle = conf.get('shuffle', True)
data_names = conf.get("data_names", "speech,text")
data_types = conf.get("data_types", "kaldi_ark,text")
- dataset = AudioDataset(scp_lists, data_names, data_types, frontend_conf=frontend_conf, shuffle=shuffle, mode=mode)
+
+ pre_hwfile = conf.get("pre_hwlist", None)
+ pre_prob = conf.get("pre_prob", 0) # unused yet
+
+ hw_config = {"sample_rate": conf.get("sample_rate", 0.6),
+ "double_rate": conf.get("double_rate", 0.1),
+ "hotword_min_length": conf.get("hotword_min_length", 2),
+ "hotword_max_length": conf.get("hotword_max_length", 8),
+ "pre_prob": conf.get("pre_prob", 0.0)}
+
+ if pre_hwfile is not None:
+ pre_hwlist = []
+ with open(pre_hwfile, 'r') as fin:
+ for line in fin.readlines():
+ pre_hwlist.append(line.strip())
+ else:
+ pre_hwlist = None
+
+ dataset = AudioDataset(scp_lists,
+ data_names,
+ data_types,
+ frontend_conf=frontend_conf,
+ shuffle=shuffle,
+ mode=mode,
+ )
filter_conf = conf.get('filter_conf', {})
filter_fn = partial(filter, **filter_conf)
dataset = FilterIterDataPipe(dataset, fn=filter_fn)
if "text" in data_names:
- vocab = {'vocab': dict, 'seg_dict': seg_dict, 'punc_dict': punc_dict, 'bpe_tokenizer': bpe_tokenizer}
+ vocab = {'vocab': dict, 'seg_dict': seg_dict, 'punc_dict': punc_dict, 'bpe_tokenizer': bpe_tokenizer, 'hw_config': hw_config}
tokenize_fn = partial(tokenize, **vocab)
dataset = MapperIterDataPipe(dataset, fn=tokenize_fn)
--
Gitblit v1.9.1