-
Hey! Thank you so so much for this repo and great work, this is what the world needs right now, I have been waiting for such a great foundation model for years!
When wanting to use vanilla KV cache…
-
I am currently running a training approach on 4xV100 with 32 GB. I am using a dataset in the style of LJSpeech and the the
finetuning training script. When I use a `batch size of 8,` I get OOM errors…
-
On many locations I observed a dotted circle in the Khmer word, and it does not look like a Khmer character. Investigating further, it looks like rendering Khmer with the NotoSans font does not match …
-
I've been using Version 2.1.1 and it would process 1 hour of audio around 15 minutes or so.
In version 3.0.1, it's been more than 1.5 hours and its still not done for 1 hour of audio.
In both …
-
**Purpose**: This issue compiles meeting notes for the Gno Core Staff's recurring meetings.
**Process**:
1. **Drafting**: Notes are initially taken in Hackmd or Google Docs during meetings.
2. *…
moul updated
10 hours ago
-
Hi,
I've trained my own dataset with 2 gpus on the same devices following [here](https://huggingface.co/speechbrain/spkrec-ecapa-voxceleb).
But I am confused about how to generate speaker embedding…
-
Bonjour,
I am trying to evaluate the fine-tuned segmentation model based on `pyannote/segmentation-3.0`.
The model seems to be training fine (DER going down) but for some reason when I try to inst…
-
### 🐛 Describe the bug
The code below is train.py
`
import os
import torch
import numpy as np
from torch.utils.data import DataLoader
from torch.utils.tensorboard import SummaryWriter
fr…
-
**Is your feature request related to a problem? Please describe.**
One problem I come across often is, that I can't verify already known speakers from other files, since inference only yields label…
-
Thank you for your work! Is there any ETA on when the training and inference code will become available?