Create training.sh

training.sh

@@ -0,0 +1,21 @@
+export TRAIN_MANIFEST_PATH="<TRAINING MANIFEST JSON>"
+export DEV_MANIFEST_PATH="<VALIDATION MANIFEST JSON>"
+export TOKENIZER_PATH="<TOKENIZER FOLDER>"
+export HYDRA_FULL_ERROR=1
+python [NEMO_GIT_FOLDER]/examples/asr/asr_ctc/speech_to_text_ctc_bpe.py --config-path=[NEMO_GIT_FOLDER]/examples/asr/conf/conformer/ --config-name=conformer_ctc_bpe \
+    model.train_ds.manifest_filepath=${TRAIN_MANIFEST_PATH} \
+    model.validation_ds.manifest_filepath=${DEV_MANIFEST_PATH} \
+    model.tokenizer.dir=${TOKENIZER_PATH} \
+    model.tokenizer.type=wpe \
+    trainer.devices=4 \
+    trainer.accelerator="gpu" \
+    trainer.strategy="ddp" \
+    trainer.max_epochs=1000 \
+    model.optim.name="adamw" \
+    model.optim.lr=0.001 \
+    model.optim.betas=[0.9,0.999] \
+    model.optim.weight_decay=0.0001 \
+    model.optim.sched.warmup_steps=2000 \
+    exp_manager.exp_dir=results/ \
+    exp_manager.create_wandb_logger=False \
+    exp_manager.resume_if_exists=true