speech_recognition/FunASR
1
0
Fork 0
mirror of https://github.com/modelscope/FunASR synced 2025-09-15 14:48:36 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

Merge pull request #593 from alibaba-damo-academy/dev_lhn

Browse Source 
Dev lhn
This commit is contained in:
hnluo 2023-06-05 17:38:24 +08:00 committed by GitHub
commit 19dcbc2d46
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 2 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
funasr/datasets/large_datasets/build_dataloader.py
View File

@ -77,12 +77,13 @@ class LargeDataLoader(AbsIterFactory):
bpe_tokenizer = SentencepiecesTokenizer(args.bpemodel)
self.dataset_conf = args.dataset_conf
self.frontend_conf = args.frontend_conf
self.speed_perturb = args.speed_perturb if hasattr(args, "speed_perturb") else None
logging.info("dataloader config: {}".format(self.dataset_conf))
batch_mode = self.dataset_conf.get("batch_mode", "padding")
data_list = args.train_data_file if mode == "train" else args.valid_data_file
self.dataset = Dataset(data_list, symbol_table, seg_dict, punc_dict, bpe_tokenizer,
self.dataset_conf, self.frontend_conf,
speed_perturb=args.speed_perturb if mode == "train" else None,
speed_perturb=self.speed_perturb if mode == "train" else None,
mode=mode, batch_mode=batch_mode)
def build_iter(self, epoch, shuffle=True):