-
Goal is to have transcription be done for .mp3 file into text file.
We want to see what transcription solution is best so that the process can be added into our automation chain
The idea is to integ…
-
max number of tokens I am able to run thru bark generate_text_semantic() is about 40, ~ 24 words or so.
I looked thru the code and noticed that generate_text_semantic() clips anything over 256 and…
xvdp updated
8 months ago
-
Hey,
if i want to train my model with costum audios and promts via metadata i just get this traceback:
> PicklingError: Can't pickle : import of module 'metadata_module' failed
Traceback (most re…
-
**Describe the bug**
Audios generated for `gu-IN` locale using voice `gu-IN-DhwaniNeural` contains about 3 sec silence at the end of audio file. The same generation, performed using `gu-IN-NiranjanNe…
-
It would be ideal to enable the user to convert the current draft files from "one chapter per cell" to "one verse per cell", "interlinear", "one pericope per cell", "one book per cell", etc.
We need …
-
Hi,
I've recently created a dataset using speech-to-text APIs on custom documents. The dataset consists of 1,000 audio samples, with 700 designated for training and 300 for testing. In total, this eq…
-
I cannot get text swapping to work during video composition, I have tried both cutout(l1, l2) and subclip(l1, l2) with no success as seen below. My output is a video with all 3 texts laying over eacho…
-
Loading text model from ./models\text_2.pt to cuda
Loading coarse model from ./models\coarse_2.pt to cuda
Loading fine model from ./models\fine_2.pt to cuda
Launching Bark UI Enhanced v0.7.4 Server…
-
### New Feature Summary
With a number of recent development, I'd like to propose more vocab types that are subcategories of `TextDocument` (all names are tentative in the proposal)
- `Transcript`:…
-
First of all, I have to thank you for the great library, without which I can't imagine working on my project.
I'm using the stable version 3.0.12.
I've encountered one problem with ID 3 tags of MP3 …