SpeechBrain

Topic	Replies	Views	Activity
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	893	April 19, 2021
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	444	April 19, 2021
ModuleNotFoundError: No module named 'parse_data' Help Wanted	7	20	July 28, 2021
Test embeddings change in VoxCeleb recipe Help Wanted	0	11	July 27, 2021
ValueError: Loss is not finite and patience is exhausted Help Wanted	5	36	July 27, 2021
Individual diarisation pipeline steps? Help Wanted	8	240	July 26, 2021
Can I download all tutorial ipynb files from one place? Help Wanted	1	15	July 26, 2021
Using DDP with an Iterable dataset Help Wanted	0	10	July 26, 2021
Ｇet a sox_io error on ubuntu Help Wanted	8	93	July 23, 2021
Using count-based language models Help Wanted	2	29	July 21, 2021
Inference time single GPU vs multiple GPU Help Wanted	1	27	July 21, 2021
How can I use my trained model after 4th step? Help Wanted	2	43	July 20, 2021
OSError: Tensors should have same dimensions except for last one [on custom model]	2	24	July 20, 2021
Problem with defining pretrained_path in ASR train.yaml Help Wanted	2	48	July 19, 2021
Speech enhancement model inference	3	47	July 19, 2021
Using pretrained croatian model for speech recognition Help Wanted	3	38	July 17, 2021
Skip using pre-trained ASR model Help Wanted	2	40	July 15, 2021
How to run the pre-trained model in Matlab? Help Wanted	1	29	July 15, 2021
Loading data from a single file with for example hdf5 Help Wanted	6	39	July 13, 2021
Spkrec-ecapa-voxceleb is using mel filterbanks instead of MFCCs Speaker ID and Verification	2	36	July 10, 2021
Speaker Diarisation for the non-Technical Help Wanted	1	57	July 9, 2021
Expected speed on CPU and GPU?	10	278	July 9, 2021
Failing at transcribing a 10 minute audio file Help Wanted	4	272	July 9, 2021
Difference between ctc_lin and seq_lin Help Wanted	1	42	July 9, 2021
Tracking gradient w.r.t. to input audio sample: Fbank breaks computation graph Help Wanted	2	32	July 7, 2021
How to get model trained on GPU Help Wanted	4	48	July 6, 2021
Fine tuning a pre-trained model using GPU Help Wanted	5	85	July 4, 2021
Missing files in VoxCeleb recipes Help Wanted	1	26	July 2, 2021
Error (speech_separation project): mse_loss function, predictions and targets don't have the same length Help Wanted	3	30	June 30, 2021
Sentencepiece and fine-tuning Help Wanted	0	35	June 28, 2021

SpeechBrain: A Community Roadmap

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

893

April 19, 2021

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

444

April 19, 2021

ModuleNotFoundError: No module named 'parse_data'