chore: import upstream snapshot with attribution

examples/speechlm2/salm_asr_decoder_train.py

@@ -0,0 +1,48 @@
+# Copyright (c) 2025, NVIDIA CORPORATION.  All rights reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+import os
+
+import torch
+from lightning.pytorch import Trainer
+from omegaconf import OmegaConf
+
+from nemo.collections.speechlm2 import DataModule, SALMDataset
+from nemo.collections.speechlm2.models.salm_asr_decoder import SALMWithAsrDecoder
+from nemo.core.config import hydra_runner
+from nemo.utils.exp_manager import exp_manager
+from nemo.utils.trainer_utils import resolve_trainer_cfg
+
+torch.cuda.set_device(int(os.environ["LOCAL_RANK"]))
+
+
+@hydra_runner(config_path="conf", config_name="salm")
+def train(cfg):
+    OmegaConf.resolve(cfg)
+    torch.distributed.init_process_group(backend="nccl")
+    torch.set_float32_matmul_precision("medium")
+    trainer = Trainer(**resolve_trainer_cfg(cfg.trainer))
+    log_dir = exp_manager(trainer, cfg.get("exp_manager", None))
+    OmegaConf.save(cfg, log_dir / "exp_config.yaml")
+
+    with trainer.init_module():
+        model = SALMWithAsrDecoder(OmegaConf.to_container(cfg.model, resolve=True))
+
+    dataset = SALMDataset(tokenizer=model.tokenizer)
+    datamodule = DataModule(cfg.data, tokenizer=model.tokenizer, dataset=dataset)
+
+    trainer.fit(model, datamodule)
+
+
+if __name__ == "__main__":
+    train()