Update run_speech_recognition_ctc.py
Browse files
run_speech_recognition_ctc.py
CHANGED
|
@@ -401,8 +401,7 @@ def main():
|
|
| 401 |
data_args.dataset_name,
|
| 402 |
data_args.dataset_config_name,
|
| 403 |
split=data_args.train_split_name,
|
| 404 |
-
use_auth_token=data_args.use_auth_token
|
| 405 |
-
cache_dir="../downloaded_data/"
|
| 406 |
)
|
| 407 |
|
| 408 |
if data_args.audio_column_name not in raw_datasets["train"].column_names:
|
|
@@ -428,7 +427,6 @@ def main():
|
|
| 428 |
data_args.dataset_config_name,
|
| 429 |
split=data_args.eval_split_name,
|
| 430 |
use_auth_token=data_args.use_auth_token,
|
| 431 |
-
cache_dir="../downloaded_data/"
|
| 432 |
)
|
| 433 |
|
| 434 |
if data_args.max_eval_samples is not None:
|
|
@@ -609,7 +607,7 @@ def main():
|
|
| 609 |
prepare_dataset,
|
| 610 |
remove_columns=next(iter(raw_datasets.values())).column_names,
|
| 611 |
batch_size=-1,
|
| 612 |
-
desc="preprocess datasets"
|
| 613 |
)
|
| 614 |
|
| 615 |
def is_audio_in_length_range(length):
|
|
|
|
| 401 |
data_args.dataset_name,
|
| 402 |
data_args.dataset_config_name,
|
| 403 |
split=data_args.train_split_name,
|
| 404 |
+
use_auth_token=data_args.use_auth_token
|
|
|
|
| 405 |
)
|
| 406 |
|
| 407 |
if data_args.audio_column_name not in raw_datasets["train"].column_names:
|
|
|
|
| 427 |
data_args.dataset_config_name,
|
| 428 |
split=data_args.eval_split_name,
|
| 429 |
use_auth_token=data_args.use_auth_token,
|
|
|
|
| 430 |
)
|
| 431 |
|
| 432 |
if data_args.max_eval_samples is not None:
|
|
|
|
| 607 |
prepare_dataset,
|
| 608 |
remove_columns=next(iter(raw_datasets.values())).column_names,
|
| 609 |
batch_size=-1,
|
| 610 |
+
desc="preprocess datasets"
|
| 611 |
)
|
| 612 |
|
| 613 |
def is_audio_in_length_range(length):
|