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

up (#13733)

Browse Source
This commit is contained in:
Patrick von Platen
2021-09-24 18:32:35 +02:00
committed by GitHub
parent 38580455de
commit 493643fff8
2 changed files with 2 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
examples/pytorch/speech-recognition/README.md
View File

@@ -81,7 +81,7 @@ of **0.35**.
The following command shows how to fine-tune [XLSR-Wav2Vec2](https://huggingface.co/transformers/master/model_doc/xlsr_wav2vec2.html) on [Common Voice](https://huggingface.co/datasets/common_voice) using 8 GPUs in half-precision. The following command shows how to fine-tune [XLSR-Wav2Vec2](https://huggingface.co/transformers/master/model_doc/xlsr_wav2vec2.html) on [Common Voice](https://huggingface.co/datasets/common_voice) using 8 GPUs in half-precision.
```bash ```bash
python -m torch.distributed.launch \ OMP_NUM_THREADS=1 python -m torch.distributed.launch \
--nproc_per_node 8 run_speech_recognition_ctc.py \ --nproc_per_node 8 run_speech_recognition_ctc.py \
--dataset_name="common_voice" \ --dataset_name="common_voice" \
--model_name_or_path="facebook/wav2vec2-large-xlsr-53" \ --model_name_or_path="facebook/wav2vec2-large-xlsr-53" \

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

@@ -103,12 +103,6 @@ class ModelArguments:
"vectors will be masked along the time axis. This is only relevant if ``apply_spec_augment is True``." "vectors will be masked along the time axis. This is only relevant if ``apply_spec_augment is True``."
}, },
) )
gradient_checkpointing: Optional[bool] = field(
default=False,
metadata={
"help": "If True, use gradient checkpointing to save memory at the expense of slower backward pass."
},
)
layerdrop: Optional[float] = field(default=0.0, metadata={"help": "The LayerDrop probability."}) layerdrop: Optional[float] = field(default=0.0, metadata={"help": "The LayerDrop probability."})
ctc_loss_reduction: Optional[str] = field( ctc_loss_reduction: Optional[str] = field(
default="mean", metadata={"help": "The way the ctc loss should be reduced. Should be one of 'mean' or 'sum'."} default="mean", metadata={"help": "The way the ctc loss should be reduced. Should be one of 'mean' or 'sum'."}
@@ -438,7 +432,7 @@ def main():
"hidden_dropout": model_args.hidden_dropout, "hidden_dropout": model_args.hidden_dropout,
"final_dropout": model_args.final_dropout, "final_dropout": model_args.final_dropout,
"mask_time_prob": model_args.mask_time_prob, "mask_time_prob": model_args.mask_time_prob,
"gradient_checkpointing": model_args.gradient_checkpointing, "gradient_checkpointing": training_args.gradient_checkpointing,
"layerdrop": model_args.layerdrop, "layerdrop": model_args.layerdrop,
"ctc_loss_reduction": model_args.ctc_loss_reduction, "ctc_loss_reduction": model_args.ctc_loss_reduction,
"pad_token_id": processor.tokenizer.pad_token_id, "pad_token_id": processor.tokenizer.pad_token_id,