Issues
- 16
load pretrained file error in ddp mode training
#2321 opened - 4
Cannot load pretrained model when using DDP
#2316 opened - 0
push to hub whisper model
#2306 opened - 3
- 1
- 1
remove system link for windows
#2298 opened - 0
I attempted to compare the results of two different voice samples using the model I trained
#2294 opened - 1
[Feature Request]: STT Example?
#2288 opened - 8
"Couldn't find appropriate audio backend to handle URI" when training with WSJ03_mix Sepformer model
#2287 opened - 3
IndexError: list index out of range
#2286 opened - 2
- 6
Severe BUG: `pos` is unexpectedly all zero.
#2276 opened - 1
- 0
- 0
- 10
I don't know what happened
#2260 opened - 2
- 16
Checkpoint not being fully removed
#2250 opened - 4
- 1
RuntimeError: CUDA error: device-side assert triggered on own data + voxceleb1 data set for training
#2248 opened - 0
Missing Speaker Diarization interface
#2245 opened - 0
- 2
- 2
Something went wrong while I was training
#2239 opened - 2
Indexing error with DynamicBatchSampling
#2235 opened - 1
hparams_CommonVoice ASR
#2230 opened - 0
- 17
Pytorch 2.1, Requirements.txt and "RuntimeError: Couldn't find appropriate backend to handle uri".
#2225 opened - 6
- 1
Segmentation Fault from `speechbrain.pretrained.vad.from_hparams` in Python 3.11.4 official image
#2212 opened - 0
- 1
I get a none noise.csv
#2208 opened - 0
- 2
How to specify gpu to run?
#2202 opened - 0
- 2
- 3
I don't know what happened during training
#2186 opened - 5
- 5
[Bug]: Causal transformer encoder
#2182 opened - 4
- 1
- 6
- 1
[Bug]: Unable to do Automatic Speech Recognition / Speech-to-Text over more than 30 sec of the audio files
#2143 opened - 6
[Bug]: difference in conformer model train using speechbrain version-0.5.11 and version-0.5.14
#2141 opened - 1
- 3
unable to run pytest tests
#2131 opened - 4
[Bug]: Torchscript provides a wrong output
#2129 opened - 2
- 8
KeyError: 'split_ratio'
#2114 opened - 7