-
Hello,
Thank you for your work on WavLM.
I try to reproduce the results but I have some difficulties.
First of all, I don't undestand exactly the difference between scores displayed in differen…
-
### Description
Train ECAPA-TDNN on adults' and children's voices
### Tasks
- [ ] explore the impact of training data window on speaker diarization performance (in a child-adult setting) and on spe…
-
Hi,
In terms of speaker verification, when comparing two audio files with different voices by using the embedding does the speech have to be the same text spoken (text dependence) ?
-
Does the speech pre-training considers speech-to-text task? Or is the model being trained for speaker verification?
-
运行from modelscope.msdatasets import MsDataset出现报错，详细报错为：
Traceback (most recent call last):
File "/private/CVPR_Anti_UAV/modelscope/utils/ast_utils.py", line 508, in _get_single_file_scan_result
…
-
I applied the last firmware update on Ubuntu 22.04 which caused:
1. 'Failed ME firmware' update screen on boot
2. Integrated audio (speakers + mic) stopped working
I tried various things with no …
-
**Task**: SPK
**Recipe:** `egs2/voxceleb/spk1`
Hi all,
Currently I'm trying to reproduce @Jungjee work of training an ecapa + wavlm SPK model, freezing the frontend, with 8kHz audio. I tried to…
-
python verification.py --model_name ecapa_tdnn --wav1 vox1_data/David_Faustino/hn8GyCJIfLM_0000012.wav --wav2 vox1_data/Josh_Gad/HXUqYaOwrxA_0000015.wav
2023-08-03 18:48:40 | INFO | fairseq.tasks.te…
-
When I try to run speaker detection in v 0.24, I get this error
ERROR: Unable to execute task for queue item TranslationofLiJingQiA.wav(SpeakerDetection)-1721905998.6038613
Traceback (most recent…
-
### Question
The project I've been working on for the part few months is now ready-enough to reveal to the world. Transformers.js is an essential part of it, and I just want to say thank you for yo…