Best free speech-to-text AI with YouTube videos processing support

Here he is: Whisper Jax AI

Whisper JAX is an optimised implementation of the Whisper model by OpenAI. It runs on JAX with a TPU v4-8 in the backend.

Key features and advantages include:

  • Fast performance: Over 70x faster than PyTorch on an A100 GPU
  • Accurate transcription: Provides accurate transcription of audio files
  • Progress bar: Displays progress of transcription through a progress bar
  • Create your own inference endpoint: To skip the queue, users can create their own inference endpoint using the Whisper JAX repository.

Use cases for Whisper JAX include:

  • Transcribing audio files quickly and accurately
  • Improving the efficiency of transcription services
  • Streamlining the transcription process for businesses and individuals.

Whisper Jax GitHub introduction with python

Whisper JAX vs PyTorch 

Комментарии

Отправить комментарий

Популярные сообщения из этого блога

Data Table Filters within Charts in Power BI

Изображение
To show underlying data for a chart visualization in Power BI, follow these steps: Select the chart visual that you want to view the underlying data for. Click on the "ellipses" (...) at the top right corner of the visual to open the dropdown menu. From the dropdown menu, select "Show as a table" option. Power BI will then display a table with the underlying data for the chart visual. You can scroll through the table to view all the data. If you want to export the underlying data to a CSV or Excel file, click on the "Export data" button at the top right corner of the table. If  you need to show background data related to some point at the chart, use "Show data point as a table" from chart figure context menu. The underlying data depends on selected Legend data field columns and source data table cannot be created by selecting several records from a chart.
Далее...

Beneficiaries and Disiribution database

Изображение
<?xml version="1.0" encoding="utf-8" ?> <!-- SQL XML created by WWW SQL Designer, https://github.com/ondras/wwwsqldesigner/ --> <!-- Active URL: https://sql.toad.cz/?keyword=default --> <sql> <datatypes db="mssql"> <group label="Integer" color="rgb(238,238,170)"> <type label="TinyInt" length="0" sql="tinyint" re="INT" quote="" bytes="1" note="Integer data: 0 to 255"/> <type label="SmallInt" length="0" sql="smallint" re="INT" quote="" bytes="2" note="Integer data: -32,768 to 32,767"/> <type label="Int" length="0" sql="int" re="INT" quote="" bytes="4" note="Integer data: -2,147,483,648 to 2,147,483,647"/> <type label="BigInt" length="0" sql=...
Далее...