Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Problema al transcribir Japones #38

Open
Jack-479 opened this issue Jul 22, 2024 · 1 comment
Open

Problema al transcribir Japones #38

Jack-479 opened this issue Jul 22, 2024 · 1 comment

Comments

@Jack-479
Copy link

no genera tiempos de subtítulos, genera un archivo de texto plano, ademas al realizar una transcripción de archivo de 01 horas a 01:30 lo realiza en un tiempo de 5 a 6 horas aprox. utilizando un modelo pequeño inclusive, lo hago en un Mac air M1.

al ejecutar Deepgram si bien es muy rápido, el texto transcrito viene lleno de errores de ortografía y gramaticales

@Marksdo
Copy link
Owner

Marksdo commented Jul 23, 2024

Here are some settings to improve transcription speed:

1. Use Medium and Small model types.

2. Use fine-tuned Japanese language models (you may need to switch between several fine-tuned models to find the one that best suits your speech scenario).

image

3. Enable the GPU acceleration option for Apple Silicon machines.

image

4. Use the Fast template for the Extra parameter.

image

5. Use the Quick Cut feature to split long videos into smaller segments of less than 30 minutes (Cut on silent piece), and select chunk-based transcription in the strategy module.

image image

6. Plug in the laptop's power.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants