# See the License for the specific language governing permissions and # limitations under the License. # You may obtain a copy of the License at # 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. # Licensed under the Apache License, Version 2.0 (the "License") # you may not use this file except in compliance with the License. # Copyright (c) 2020, NVIDIA CORPORATION. Dataset Creation Tool Based on CTC-Segmentation.Applying BPE Tokenization, Batching, Bucketing and Padding.Data Cleaning, Normalization & Tokenization.Training The Token Classification model.Data Input for Token Classification Model.Token Classification (Named Entity Recognition) Model.Training Punctuation and Capitalization Model.NeMo Speaker Diarization Configuration Files.NeMo Speech Classification Configuration Files.Preparing Custom Speech Classification Data.Evaluate by Beam Search Decoding and N-gram LM.Recommendations For Optimization And FAQs.Using Speech Command Recognition Task For ASR Models.Using Optimized Pretrained Models With NeMo.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |