SUMIN/HuggingFace_transformer
1
0
Fork 0
Code Issues Pull Requests Actions 7 Packages Projects Releases Wiki Activity

Removing extra space in large command for speech-pretraining example (#38705)

Browse Source 
Removing extra space in Large command
This commit is contained in:
Dianana
2025-06-24 06:24:56 -06:00
committed by GitHub
parent d3d835d4fc
commit 4f650040a6
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
examples/pytorch/speech-pretraining/README.md
View File

@@ -129,7 +129,7 @@ To pre-train `"large-sized"` Wav2Vec2 model, *e.g.* [facebook/wav2vec2-large-lv6
on [librispeech_asr](https://huggingface.co/datasets/librispeech_asr), the following command can be run: on [librispeech_asr](https://huggingface.co/datasets/librispeech_asr), the following command can be run:
```bash ```bash
accelerate launch run_wav2vec2_pretraining_no_trainer.py \ accelerate launch run_wav2vec2_pretraining_no_trainer.py \
--dataset_name=librispeech_asr \ --dataset_name=librispeech_asr \
--dataset_config_names clean clean other \ --dataset_config_names clean clean other \
--dataset_split_names train.100 train.360 train.500 \ --dataset_split_names train.100 train.360 train.500 \
@@ -141,7 +141,7 @@ accelerate launch run_wav2vec2_pretraining_no_trainer.py \
--weight_decay=0.01 \ --weight_decay=0.01 \
--max_duration_in_seconds=20.0 \ --max_duration_in_seconds=20.0 \
--min_duration_in_seconds=2.0 \ --min_duration_in_seconds=2.0 \
--model_name_or_path=./ --model_name_or_path=./ \
--logging_steps=1 \ --logging_steps=1 \
--saving_steps=10000 \ --saving_steps=10000 \
--per_device_train_batch_size=2 \ --per_device_train_batch_size=2 \