-
### Describe the bug
Using a YourTTS model which has been fine-tuned on a VCTK format dataset with a single speaker.
This model requires that the speaker_embeddings be given as d_vectors for infer…
-
### Describe the bug
I was validating the resolution of bug #3224 which I suspect was fixed in commit 4d0f53d2ee572210c20401657aa1606c7c32189c and got a new unexpected error from the same code. I e…
-
Thanks for interesting paper and nice repo.
I got question about pitch encoder.
In pitch encoder, it takes inputs as ying, spectrogram lengths and speaker embedding.
But its quite wired thing as …
-
Running the diarization example in google colab, pyannote version 3.1.0 outputs:
ImportError: 'onnxruntime' must be installed to use 'hbredin/wespeaker-voxceleb-resnet34-LM' embeddings.
Thank yo…
-
Symptom:
```
% ptpython
>>> sys.version
'3.10.8 (main, Oct 21 2022, 22:22:30) [Clang 14.0.0 (clang-1400.0.29.202)]'
>>> import soundcard as sc
>>> sc.all_speakers()
[]
>>> sc.all_microph…
-
When transcribing & diarizing podcasts with WhisperX, on several different podcasts, **I've encountered that WhisperX won't create any output files (.srt, .vtt, etc).**
In these cases, the **below*…
7k50 updated
10 months ago
-
E: we should mostly have all the English text subtitled now, massive thanks to everyone that helped out below!
Now we just need to test with this pack, & make sure all the texts are translated/cent…
-
(Click to enlarge)
---
Hi all,
My previous work for Zynaddsubfx has sam…
-
I disabled `postnet` then tried to train text-to-spec but the logs are showing postnet. It shouldn't show up if I request not to use it.
```
config/everyvoice-text-to-spec.yaml: use_postnet: fal…
-
### System Info
- `transformers` version: 4.33.1
- Platform: Linux-6.2.0-32-generic-x86_64-with-glibc2.35
- Python version: 3.10.12
- Huggingface_hub version: 0.16.4
- Safetensors version: 0.3.…