-
请问声纹识别复现的是without s-norm的model吗?with s-norm的代码没有吗?
-
Hi, I export the ecapa-tdnn model to onnx and use onnxruntime to inference. But the inference speed is slower than pytorch. Does anybody konw why?
-
Hi,
I am trying to run the diarization recipe but `No recording IDs found! Please check if meta_data json file is properly generated.` is being shown. I came to know that this is due due to incorrec…
-
I can't runing with MFCC features
My config:
dataset_conf:
batch_size: 32
num_class: 10
num_workers: 8
min_duration: 0.5
chunk_duration: 3
do_vad: False
sample_rate: 16000
…
-
I want to use my own model but get the following error:
`model1 = torch.load('RCTNet.h5')
target_layers = [model1.speaker_encoder.pre_tdnn.layer3]
img_path = "./eagle.jpg"
test_image = Image.o…
-
Running this in wsl2 using an RTX3090.
It is processing "word_hyp, word_ts_hyp = asr_decoder_ts.run_ASR(asr_model)"
on a 20-minute wav file, is but never seems to terminate.
```
@hydra_runn…
-
大佬我执行 python3 infer_contrast.py --audio_path1=audio/a_1.wav --audio_path2=audio/b_2.wav 的时候报 ValueError: The ``path`` (models/ecapa_tdnn/model.pdparams) to load model not exists. 同时我没有安装PaddlePaddle的I…
-
This is an issue for developing a decent framework for speaker verification under ESPnet2.
We sometimes call it 'speaker id' but just in case, on the evaluation side identification and verificatio…
-
Hi,
I'm trying to fit my custom dataset following the tutorial from https://colab.research.google.com/drive/1UwisnAjr8nQF3UnrkIJ4abBMAWzVwBMh?usp=sharing.
I don't need the environment corrupti…
-
Hi,
I really liked the prosody transfer capabilities of the new GST based model, but it is not able to handle all types of voices like the ECAPA model, for example I tried synthesizing some High pi…