riaz.somc/transformers
1
0
Fork 0
mirror of https://github.com/huggingface/transformers.git synced 2025-07-31 02:02:21 +06:00
Code Issues Actions 23 Packages Projects Releases Wiki Activity

[Examples] Fix typos in run speech recognition seq2seq (#19514)

Browse Source
This commit is contained in:
Sanchit Gandhi 2022-10-12 15:33:22 +01:00 committed by GitHub
parent 72153ba611
commit eefcecaa35
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 4 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
examples/pytorch/speech-recognition/run_speech_recognition_seq2seq.py
View File

@ -195,7 +195,7 @@ class DataCollatorSpeechSeq2SeqWithPadding:
Data collator that will dynamically pad the inputs received.
Args:
processor ([`Wav2Vec2Processor`])
The processor used for proccessing the data.
The processor used for processing the data.
decoder_start_token_id (`int`)
The begin-of-sentence of the decoder.
"""
@ -204,7 +204,7 @@ class DataCollatorSpeechSeq2SeqWithPadding:
decoder_start_token_id: int
def __call__(self, features: List[Dict[str, Union[List[int], torch.Tensor]]]) -> Dict[str, torch.Tensor]:
# split inputs and labels since they have to be of different lenghts and need
# split inputs and labels since they have to be of different lengths and need
# different padding methods
input_features = [{"input_values": feature["input_values"]} for feature in features]
label_features = [{"input_ids": feature["labels"]} for feature in features]
@ -271,7 +271,7 @@ def main():
transformers.utils.logging.set_verbosity_info()
logger.info("Training/evaluation parameters %s", training_args)
# 3. Detecting last checkpoint and eventualy continue from last checkpoint
# 3. Detecting last checkpoint and eventually continue from last checkpoint
last_checkpoint = None
if os.path.isdir(training_args.output_dir) and training_args.do_train and not training_args.overwrite_output_dir:
last_checkpoint = get_last_checkpoint(training_args.output_dir)
@ -360,7 +360,7 @@ def main():
if model_args.freeze_feature_encoder:
model.freeze_feature_encoder()
# 6. Resample speech dataset if necassary
# 6. Resample speech dataset if necessary
dataset_sampling_rate = next(iter(raw_datasets.values())).features[data_args.audio_column_name].sampling_rate
if dataset_sampling_rate != feature_extractor.sampling_rate:
raw_datasets = raw_datasets.cast_column(