|
| 1 | +# Copyright (c) 2025, NVIDIA CORPORATION. All rights reserved. |
| 2 | +# |
| 3 | +# Licensed under the Apache License, Version 2.0 (the "License"); |
| 4 | +# you may not use this file except in compliance with the License. |
| 5 | +# You may obtain a copy of the License at |
| 6 | +# |
| 7 | +# http://www.apache.org/licenses/LICENSE-2.0 |
| 8 | +# |
| 9 | +# Unless required by applicable law or agreed to in writing, software |
| 10 | +# distributed under the License is distributed on an "AS IS" BASIS, |
| 11 | +# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. |
| 12 | +# See the License for the specific language governing permissions and |
| 13 | +# limitations under the License. |
| 14 | + |
| 15 | +# The script to be run. |
| 16 | +script: # Script path to run relative to directory |
| 17 | +script_config: # Training config file for the script. ipl_epoch_stopper_callback should be provided in the config |
| 18 | +inference_config: # Inference config file of unlabeled data for transcribe_speech_parallel |
| 19 | + |
| 20 | +exp_name: null # populated by exp_manager.name if not provided |
| 21 | +results_dir: # Where to store the results of the run |
| 22 | + |
| 23 | +# Path to the local NeMo repository. This is used to locate scripts and configs from NeMo. |
| 24 | +# To set this up: |
| 25 | +# 1. Clone the NeMo repository: |
| 26 | +# git clone https://github.com/NVIDIA/NeMo.git /your/desired/path/to/nemo |
| 27 | +# 2. Set the path here: |
| 28 | +# Make sure this path is valid and NeMo is up to date if you're using its scripts. |
| 29 | +nemo_directory: # Nemo directory path |
| 30 | +do_average: # Boolean value indicating whether to do average of checkpoints for pseudo-label generation |
| 31 | +p_cache: # Probability with which update pseudo-labeled set |
| 32 | +num_ipl_epochs: # How many epochs do pseudo-labeling |
| 33 | + |
| 34 | +# Optional arguments |
| 35 | +num_runs: |
| 36 | +num_gpus: |
| 37 | +num_tasks_per_node: |
| 38 | +max_runtime: # Specify for clusters |
| 39 | + |
| 40 | +######################################################################################################################## |
| 41 | + |
| 42 | +executor: slurm # or local |
| 43 | + |
| 44 | +USER: |
| 45 | + |
| 46 | +# Fields for cluster run |
| 47 | +ssh_tunnel: |
| 48 | + host: |
| 49 | + # ------------------------------- Fill this up! ------------------------------- |
| 50 | + user: "${USER}" # your username; or resolved from ${USER} environment variable ; or can be null which resolved from ${USER} environment variable |
| 51 | + job_dir: "" # Job directory to keep created files |
| 52 | + identity: "" |
| 53 | + # ----------------------------------------------------------------------------- |
| 54 | + |
| 55 | +account: |
| 56 | +partition: |
| 57 | +job_name_prefix: |
| 58 | + |
| 59 | +containers: |
| 60 | + asr: # Container image |
| 61 | + |
| 62 | + |
| 63 | +env_vars: |
| 64 | + - 'TOKENIZERS_PARALLELISM=' |
| 65 | + - 'AIS_ENDPOINT=' |
| 66 | + - 'LHOTSE_AUDIO_DURATION_MISMATCH_TOLERANCE=' |
| 67 | + - 'TORCH_CUDNN_V8_API_ENABLED=' |
| 68 | + - 'PYTORCH_CUDA_ALLOC_CONF=' |
| 69 | + - 'HYDRA_FULL_ERROR=1' |
| 70 | + |
| 71 | +required_env_vars: |
| 72 | + - 'HF_TOKEN=' |
| 73 | + - 'WANDB_KEY=' |
| 74 | + |
| 75 | +mounts: |
| 76 | + # Replace with your own paths in your cluster config |
| 77 | + - /path/to/mount:/where/to/mount/ |
| 78 | + |
| 79 | +timeouts: |
| 80 | + partition_name: # Specify time |
0 commit comments