-
hello, when I enter the docker, run test.py. I face the error: No such file or directory: 'model/1580.iv'
root@c9c5cf113b47:/mounted# python3 test.py
Traceback (most recent call last):
File "te…
-
-
I've run speaker_verification_cosine.py and got Command terminated by signal 9 after writing scores.txt.
How can I compute EER from scores.txt?
Thanks in advance.
-
Below are the files (trials and score file with 58904064 lines) that are being produced.
Trails File(an example of contents in file):
p11_1 p11_79 target
p11_1 p11_80 target
p11_1 p11_81 targe…
-
I follow the instructions to download the datasets - VoxCeleb1 and VoxCeleb2 and concatenate the files using "cat vox1_dev* > vox1_dev_wav.zip". However, when I get the following error when I try to …
-
@joonson I saw a very strange behavior during training. The Training slows down after a few steps (generally after 50% steps in the first epoch). The Hz drops from 300+ to less than 10. At this point …
-
hello @mravanelli , thank you so much for the great work you shared.
I found that 'start' and 'stop' were all in 'train.csv' after preparing voxceleb. But when training, the default 'random_chunk' in…
-
Hello! I found that EER at vox1 is 0.69%, which is outstanding results.
But also I found in train_ecapa_tdnn.yaml that you're training and testing on the same data. In this file also I found that you…
-
If I run `python train_speaker_embeddings.py hparams/train_ecapa_tdnn.yaml` I get:
```sh
Extracting /home/allabana/stt_ws/speechbrain/samples/voxceleb_samples/wav/rirs_noises.zip to /home/allabana…
-
run.sh
```
# in this example, your images should be "$DATASET_ROOT/images-cropped/$IDENTITY_NAME/*.jpg"
DATASET_ROOT="/content/dataset"
IDENTITY_NAME="id00017"
MAX_BATCH_SIZE=8 # pick…