spectrobot

Getting Key Error while finetuning Speaker Recognition model

1

Hi @nithinraok , Please have a look into it. I am trying to finetune speaker recognition model on open source dataset. When I set train_manifest_path and dev_manifest_path both as same...

Hi, Thanks a lot for your work. I have reproduced the same for TIMIT dataset. Now I have converted that model to ONNX and then to tflite for d vector...

Unable to find and test arm-linux-androideabi-gcc binary in latest ndk for libsndfile using android_configure.sh script.

5

Hi, I am trying to run libsndfile on Android ndk 22.0 and ndk 21d. I am following the official readme and when I run ./Scripts/android_configure.sh Its giving me error as...

Hi, Thank you so much for this work. I am running speaker diarization on english dataset. I trained uisrnn model on custom english speaker's data. When I run inference multiple...

Speaker diarization gives more than two speaker while i have only two speakers in the audio file.

26

I have hindi-english mixed audio with almost 130 speakers each having 200 utterances of length between 4 sec -10 sec. I made d-vector using vgg-speaker recognition model (pre-trained given in...

Very bigger segment (chunk) size (almost 30 second each) with BatchedInferencePipeline

4

I am using BatchedInferencePipeline on a audio file of 1 hr duration and getting each segment of almost 30 sec each. When I don't use BatchedInferencePipeline, segment duration is 1-2...