decoding

游雁

2024-06-13 f97f3e8dd5b40be6faaccd9c089aea52ceba29ef

 funasr/bin/train_ds.py

@@ -66,7 +66,6 @@
    # open tf32
    torch.backends.cuda.matmul.allow_tf32 = kwargs.get("enable_tf32", True)

    rank = int(os.environ.get("RANK", 0))
    local_rank = int(os.environ.get("LOCAL_RANK", 0))
    world_size = int(os.environ.get("WORLD_SIZE", 1))

@@ -83,6 +82,8 @@
        logging.info(f"use_ddp: {use_ddp}, use_fsdp: {use_fsdp}")
        dist.init_process_group(backend=kwargs.get("backend", "nccl"), init_method="env://")
        torch.cuda.set_device(local_rank)

    rank = dist.get_rank()

    logging.info("Build model, frontend, tokenizer")
    device = kwargs.get("device", "cuda")
@@ -124,6 +125,7 @@
        use_ddp=use_ddp,
        use_fsdp=use_fsdp,
        device=kwargs["device"],
        excludes=kwargs.get("excludes", None),
        output_dir=kwargs.get("output_dir", "./exp"),
        **kwargs.get("train_conf"),
    )