MSAdapterModelZoo

关于GCU、沐曦GPGPU、MLU、0卡V100资源4月7日恢复上架的公告>>> 关于共建具身智能开源数据集的倡议>>> 关于云脑任务中统一路径访问方式的公告>>> 关于将启智集群GPU资源迁移至智算集群的公告>>>

History

Erpim 54ccc38aec update opt/nograd		10 months ago
..
conformer_adapter	update opt/nograd	10 months ago

conformer_pytorch	add conformer to official	11 months ago

README.md	update official (#33)	10 months ago

README.md

Conformer
Dataset
Environment Requirements
Model Source
Quick Start

Conformer

conformer model with training script for end-to-end speech recognition on the LibriSpeech dataset.

Dataset

LibriSpeech dataset

Environment Requirements

Hardware（Ascend/GPU/CPU）

Model Source

In this case, the source of the model definition or training script corresponding to the implementation of PyTorch is as follows:

https://github.com/jreremy/conformer

Quick Start

This case shows the Conformer model implemented by pytorch and the version converted based on MSAadpter, you can start training and evaluation as follows:

# PyTorch
# Train model from scratch:
python train.py --data_dir=../data --train_set=train-clean-100 --test_set=test-clean --checkpoint_path=model_best.pth

# MSAdapter.pytorch
# Train model from scratch:
python train.py --data_dir=../data --train_set=train-clean-100 --test_set=test-clean --checkpoint_path=model_best.pth --device[CPU/GPU/Ascend]