NVIDIA / NeMo Public

Discussions

• 2

  🙌

  Minimal example on how to use pre-trained ASR models for audio transcriptions on a laptop (without GPUs)

  okuchaiev started Jan 28, 2022 in Show and tell

  

  

  2
• 1

  🙏

  Spectrogram normalization constants

  roman-vygon asked Jan 27, 2022 in Q&A · Answered

  

  

  1
• 1

  🙏

  ASR models for Russian

  annaklyueva asked Jan 23, 2022 in Q&A · Answered

  

  

  1
• 3

  🙏

  TTS utf-8 input

  oytunturk asked Jan 23, 2022 in Q&A · Unanswered

  

  

  0
• 1

  🙏

  ASR models for Russian

  annaklyueva asked Jan 23, 2022 in Q&A · Unanswered

  

  

  0
• 1

  🙏

  Adding KenLM degrades performance

  errorfixrepeat asked Jan 2, 2022 in Q&A · Unanswered

  

  

  

  

  5
• 2

  🙏

  Multi-speaker TTS training

  oytunturk asked Jan 15, 2022 in Q&A · Unanswered

  

  

  0
• 1

  🙏

  Resegmentation in Diarization

  architlfc asked Jan 13, 2022 in Q&A · Unanswered

  

  

  0
• 1

  🙏

  MatchBoxNet for own data and labels

  monologue110 asked Nov 15, 2021 in Q&A · Unanswered

  

  

  5
• 2

  🙏

  Licence of pretrained models

  DanBmh asked Jan 25, 2021 in Q&A · Answered

  

  

  

  

  2
• 1

  💬

  Why training is not resuming from checkpoint?

  muntasir2000 started Jan 3, 2022 in General

  

  

  2
• 1

  🙏

  RAD-TTS

  Nikuson123 asked Jan 8, 2022 in Q&A · Unanswered

  

  

  0
• 1

  🙏

  Persistent error 'Module not found error: megatron.fp16'

  tanmayg asked Jan 7, 2022 in Q&A · Unanswered

  

  

  0
• 1

  💬

  MarbleNet vs noise?

  seekingdeep started Jan 6, 2022 in General

  

  

  2
• 1

  🙏

  Example for running inference using user trained TTS model

  oytunturk asked Dec 30, 2021 in Q&A · Answered

  

  

  

  

  3
• 1

  🙏

  How extracted timestamps when using a beam search decoder?

  Slava715 asked Jul 29, 2021 in Q&A · Answered

  

  

  

  

  8
• 1

  🙏

  Support for continued TTS model training

  oytunturk asked Dec 30, 2021 in Q&A · Answered

  

  

  1
• 1

  🙏

  Citrinet model with LM to reduce the WER for microphone recorded audio

  kruthikakr asked Apr 9, 2021 in Q&A · Answered

  

  

  

  

  20
• 1

  🙏

  When has the definition of `num_classes` been changed?

  whrichd asked Dec 13, 2021 in Q&A · Unanswered

  

  

  3
• 2

  🙏

  Decoding and WER evaluation

  andrusenkoau asked Dec 15, 2021 in Q&A · Unanswered

  

  

  0
• 1

  🙏

  When will mixer_tts pretrained model added?

  yuananf asked Dec 13, 2021 in Q&A · Unanswered

  

  

  0
• 1

  🙏

  Multi-Dataset Sampling for Speaker Recognition Fine-tuning

  ap48923 asked Dec 6, 2021 in Q&A · Unanswered

  

  

  1
• 1

  🙏

  How adaptive bucketing should work?

  nasretdinovr asked Dec 8, 2021 in Q&A · Answered

  

  

  

  

  5
• 1

  💬

  speaker recognition tutorial : all losses diverge :(

  pierrebedu started Nov 19, 2021 in General

  

  

  

  

  5
• 1

  🙏

  Unable to do speaker diarization with ASR

  godspirit00 asked Dec 5, 2021 in Q&A · Unanswered

  

  

  0