-
Hi there currently getting this error on Windows 11 - I have python in my path ENVIRONMENT variables and I also put in pyvenv to install a version for this. Any help would be amazing as I am excited …
-
### 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…
-
I'm using your model to train on TIMIT, my parameters are the same as yours ,such as lr、batchsize. I use the script named ‘speaker_id.py ’ to train model, and ‘compute_d_vector.py’ to get embeddings …
-
### Question
I'm trying to get ASR + segmentation to run on a mobile phone (Pixel 6A, 6GB ram). This time on Brave mobile ;-)
ASR alone works fine. But I have a question about also getting the s…
-
The base conda env is: `conda create -n unispeech python=3.8`
when I run `pip install --require-hashes -r requirements.txt` under [speaker_verification](https://github.com/microsoft/UniSpeech/tree/ma…
-
According to the WavLM paper:
([WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing](https://arxiv.org/pdf/2110.13900.pdf))
They used ECAPA-TDNN embeddings model for …
-
Hi,
I wanna use **wavlm** model to extract speaker embedding for speaker verification task. In [the paper](https://arxiv.org/pdf/2110.13900.pdf) it is mentioned that for the task of speaker verificat…
-
Hi, why not add speaker classification in speaker encoder, or use Speaker Verification feature. If I only use a speaker encoder, will there be any problems with timbral coupling?
-
Suppose I want to test the voice/numpy array/features of one speaker against seven different speakers.
Does the data of the single speaker go in the enrollment or the verification batch? Similarly…
-
When verifying the device with another device, the EX app needs to be open before the verification is started, otherwise the request is lost. This is not ideal, but there is no trivial fix for it. The…