From b15db52e4e67da8a133a67e8ffa415386de48b40 Mon Sep 17 00:00:00 2001
From: zhuyunfeng <10596244@qq.com>
Date: 星期二, 09 五月 2023 23:03:15 +0800
Subject: [PATCH] Add contributor
---
funasr/datasets/large_datasets/dataset.py | 82 ++++++++++++++++++++++++++++++++++------
1 files changed, 69 insertions(+), 13 deletions(-)
diff --git a/funasr/datasets/large_datasets/dataset.py b/funasr/datasets/large_datasets/dataset.py
index 41d34ab..8c224d8 100644
--- a/funasr/datasets/large_datasets/dataset.py
+++ b/funasr/datasets/large_datasets/dataset.py
@@ -1,9 +1,10 @@
import os
import random
-import soundfile
+import numpy
from functools import partial
import torch
+import torchaudio
import torch.distributed as dist
from kaldiio import ReadHelper
from torch.utils.data import IterableDataset
@@ -13,6 +14,7 @@
from funasr.datasets.large_datasets.datapipes.map import MapperIterDataPipe
from funasr.datasets.large_datasets.utils.filter import filter
from funasr.datasets.large_datasets.utils.padding import padding
+from funasr.datasets.large_datasets.utils.clipping import clipping
from funasr.datasets.large_datasets.utils.tokenize import tokenize
@@ -26,10 +28,11 @@
class AudioDataset(IterableDataset):
- def __init__(self, scp_lists, data_names, data_types, shuffle=True, mode="train"):
+ def __init__(self, scp_lists, data_names, data_types, frontend_conf=None, shuffle=True, mode="train"):
self.scp_lists = scp_lists
self.data_names = data_names
self.data_types = data_types
+ self.frontend_conf = frontend_conf
self.shuffle = shuffle
self.mode = mode
self.epoch = -1
@@ -98,9 +101,11 @@
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":
+ continue
else:
raise TypeError("Data type {} is not supported".format(data_type))
@@ -114,21 +119,38 @@
sample_dict["key"] = key
elif data_type == "sound":
key, path = item.strip().split()
- mat, sampling_rate = soundfile.read(path)
+ waveform, sampling_rate = torchaudio.load(path)
+ if self.frontend_conf is not None:
+ if sampling_rate != self.frontend_conf["fs"]:
+ waveform = torchaudio.transforms.Resample(orig_freq=sampling_rate,
+ new_freq=self.frontend_conf["fs"])(waveform)
+ sampling_rate = self.frontend_conf["fs"]
+ waveform = waveform.numpy()
+ mat = waveform[0]
sample_dict[data_name] = mat
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
- sample_dict[data_name] = text.strip().split()[1:]
+ segs = text.strip().split()
+ sample_dict[data_name] = segs[1:]
+ if "key" not in sample_dict:
+ sample_dict["key"] = segs[0]
yield sample_dict
self.close_reader(reader_list)
def len_fn_example(data):
- return len(data)
+ return 1
def len_fn_token(data):
@@ -142,21 +164,50 @@
def Dataset(data_list_file,
dict,
seg_dict,
+ punc_dict,
+ bpe_tokenizer,
conf,
- mode="train"):
+ frontend_conf,
+ mode="train",
+ batch_mode="padding"):
scp_lists = read_lists(data_list_file)
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, 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)
- vocab = {'vocab': dict, 'seg_dict': seg_dict}
- tokenize_fn = partial(tokenize, **vocab)
- dataset = MapperIterDataPipe(dataset, fn=tokenize_fn)
+ if "text" in data_names:
+ 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)
if shuffle:
buffer_conf = conf.get('shuffle_conf', {})
@@ -180,8 +231,13 @@
batch_size=batch_size,
len_fn=len_fn,
buffer_size=buffer_size,
- sort_size=sort_size)
+ sort_size=sort_size,
+ batch_mode=batch_mode)
- dataset = MapperIterDataPipe(dataset, fn=padding)
+ int_pad_value = conf.get("int_pad_value", -1)
+ float_pad_value = conf.get("float_pad_value", 0.0)
+ padding_conf = {"int_pad_value": int_pad_value, "float_pad_value": float_pad_value}
+ padding_fn = partial(padding, **padding_conf)
+ dataset = MapperIterDataPipe(dataset, fn=padding_fn if batch_mode == "padding" else clipping)
return dataset
--
Gitblit v1.9.1