mesut

Hi I used NeMo/scripts/dataset_processing/ljspeech/README, and i ran NeMo/scripts/dataset_processing/ljspeech/extract_ljspeech_phonemes_and_durs.sh . However alignments directory is empty. My logs; `Skipping environment setup. Assuming env name aligner exists. Starting MFA with dictionary at: /home/mesut/Documents/MFA/pretrained_models/dictionary/english_us_arpa.dict...

How to train d-vector model for using on diarization with my own data?

2

Hi Harry; I want to use d-vector for diarization with 8kHz data. I have 9000 speakers. However my loss saturate around 5 (at 250 epoch)(Should I train with more epochs?)....

Hi Can you share critical requriments like tensorflow or which needed importantly? Thanks

Hi What is the accuracy performance of algorithms. Did you publish any paper? Did you tried out of domain data, is it working on out of domain? Best regards

Hi I am developing a KWS system on STM32 F7 board. I am using this; ML-examples/cmsis-pack-examples/kws/src/main_live.cpp How can I receive response with Putty? Are there any idea. I need to...

Retraining of the KWS model

19

Hi I am trying to create a new KWS model. I trained a model on this notebook. https://github.com/tensorflow/tflite-micro/blob/main/tensorflow/lite/micro/examples/micro_speech/train/train_micro_speech_model.ipynb I moved weights to nn_model variable in kws_micronet_m.tflite.cpp. And I changed Labels.cpp...

Did you try on the out of domain data for replay attack detection? Because most of these algorithms are not working good on the real-world data which i saw. Do...