From 28a19dbc4e85d3b8a4ec2ef7483bba64d422b43f Mon Sep 17 00:00:00 2001
From: aky15 <ankeyu.aky@11.17.44.249>
Date: 星期三, 12 四月 2023 18:03:06 +0800
Subject: [PATCH] Merge remote-tracking branch 'origin/main' into dev_aky
---
funasr/datasets/large_datasets/dataset.py | 14 +++++++++++---
1 files changed, 11 insertions(+), 3 deletions(-)
diff --git a/funasr/datasets/large_datasets/dataset.py b/funasr/datasets/large_datasets/dataset.py
index 61231d2..b0e1b8f 100644
--- a/funasr/datasets/large_datasets/dataset.py
+++ b/funasr/datasets/large_datasets/dataset.py
@@ -28,10 +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
@@ -119,6 +120,11 @@
elif data_type == "sound":
key, path = item.strip().split()
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
@@ -152,21 +158,23 @@
dict,
seg_dict,
punc_dict,
+ bpe_tokenizer,
conf,
+ 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)
+ 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}
+ vocab = {'vocab': dict, 'seg_dict': seg_dict, 'punc_dict': punc_dict, 'bpe_tokenizer': bpe_tokenizer}
tokenize_fn = partial(tokenize, **vocab)
dataset = MapperIterDataPipe(dataset, fn=tokenize_fn)
--
Gitblit v1.9.1