Topic Replies Views Activity
Welcome to Speechbrain! READ ME Before Posting!
Announcements

Why a Discourse? SpeechBrain is an open-source and all-in-one speech toolkit based on PyTorch. With this Discourse, you are invited to ask questions, consider new changes, propose new directions, follow our latest new…

4 677 April 19, 2021
SpeechBrain: A Community Roadmap
Announcements

Why a Roadmap? As a community-based and open source project, SpeechBrain needs the help of its community to grow in the right direction. Opening the roadmap to our users enables the toolkit to benefit from new ideas, …

2 1635 April 19, 2021
Feature request. Iteration number in training loop.
1 15 December 6, 2021
Microphone array have a wrong position in SB tutorial
Help Wanted
0 31 December 1, 2021
Diarization problem
Help Wanted
0 16 December 1, 2021
Another way of batch sampling
0 13 November 30, 2021
Finetuning SepFormer : CUDA out of Memory Error
Help Wanted
3 137 November 29, 2021
Fbank and MFCC modules compute an extra frame
0 27 November 27, 2021
Error while training the audio data with common voice
Help Wanted
0 24 November 26, 2021
OSError: libcudart.so.10.2: cannot open shared object file: No such file or directory
Help Wanted
0 42 November 11, 2021
DNS enhance spectral map recipe question
0 33 November 8, 2021
How to get the model's gradient and wav's gradient?
2 43 November 8, 2021
Exporting to C++
General Architecture
1 52 November 5, 2021
Checkpointer Load Warning
Help Wanted
1 35 November 5, 2021
Pretraining,transfer learning
Help Wanted
7 409 November 5, 2021
Filterbank non-constant amplitudes
4 63 November 5, 2021
Evaluate doesn't return the avg loss
Help Wanted
2 34 November 4, 2021
Is Speechbrain Pytorch 1.10 compatible?
General Architecture
4 88 November 1, 2021
FORMAT OF DATA SET FOR MAKING CUSTOM LANGUAGE ASR SYSTEM (Speech Emotion and Speech to Text)
6 118 October 30, 2021
Speech enhancement model inference
9 301 October 29, 2021
Problem about Speaker Verification test batch size
Help Wanted
4 119 October 29, 2021
Pretrained ECAPA-TDNN net outputs same feature vector for different signals
Speaker ID and Verification
0 51 October 29, 2021
Use pretrained SpeechBrain model as Loss
Help Wanted
9 88 October 29, 2021
DNN Beamforming and other front-ends modules
Closed Beta Testing
17 374 October 28, 2021
RNN-T joint network significantly consuming memory and causing OOM
Help Wanted
3 66 October 27, 2021
Implementing streaming ASR
E2E Speech Recognition
8 146 October 23, 2021
Drop last batch
Help Wanted
3 64 October 22, 2021
Speechbrain/sepformer-whamr with large files
Source Separation
3 82 October 21, 2021
Delay and Sum beamforming
Speech Processing
1 44 October 21, 2021
Why log_probs need to be detached in transducer_loss
Help Wanted
3 39 October 14, 2021