# \#whisper

**URL:** https://forum.elixirforum.com/tag/whisper/4089.md

[Latest](https://forum.elixirforum.com/latest.md) · [Categories](https://forum.elixirforum.com/categories.md) · [Tags](https://forum.elixirforum.com/tags.md)

---

## [VaultChat - local-first WhatsApp archive reconstruction tool built with Phoenix LiveView](https://forum.elixirforum.com/t/vaultchat-local-first-whatsapp-archive-reconstruction-tool-built-with-phoenix-liveview/74865)

<div class="topic-metadata">

**Author:** [@arruah](https://forum.elixirforum.com/u/arruah)\
**Replies:** 0\
**Last updated:** [April 2, 2026, 7:07pm UTC](https://forum.elixirforum.com/t/vaultchat-local-first-whatsapp-archive-reconstruction-tool-built-with-phoenix-liveview/74865 "2026-04-02T19:07:12Z")

</div>

VaultChat — local-first WhatsApp archive reconstruction with Phoenix LiveView + whisper.cpp Hi everyone, I want to share an early alpha project I’ve been building: VaultChat. The problem WhatsApp exports with many voic…

---

## [High memory usage when transcribing with whisper-large-v3 in Nx/EXLA/Bumblebee](https://forum.elixirforum.com/t/high-memory-usage-when-transcribing-with-whisper-large-v3-in-nx-exla-bumblebee/71614)

<div class="topic-metadata">

**Author:** [@aime](https://forum.elixirforum.com/u/aime)\
**Replies:** 1\
**Last updated:** [July 31, 2025, 2:04pm UTC](https://forum.elixirforum.com/t/high-memory-usage-when-transcribing-with-whisper-large-v3-in-nx-exla-bumblebee/71614 "2025-07-31T14:04:36Z")

</div>

Hi, I’m trying to load Whisper models into Elixir using Nx, EXLA, and Bumblebee. I’ve encountered the following issue: When using the whisper-large-v3 model to transcribe audio files under 200 KB, the process consumes o…

---

## [Troubleshooting: Bumblebee audio transcription provides same text for few parsed webm files](https://forum.elixirforum.com/t/troubleshooting-bumblebee-audio-transcription-provides-same-text-for-few-parsed-webm-files/70214)

<div class="topic-metadata">

**Author:** [@marinakr](https://forum.elixirforum.com/u/marinakr)\
**Replies:** 3\
**Last updated:** [April 2, 2025, 5:48am UTC](https://forum.elixirforum.com/t/troubleshooting-bumblebee-audio-transcription-provides-same-text-for-few-parsed-webm-files/70214 "2025-04-02T05:48:39Z")

</div>

Hi, I am trying to use Bumblebee to transcript audio to text I have few multiple \*.webm files with audio that sounds like ‘text audio with Bumblebee’, ‘one, two, three, four, five’, etc I can reproduce it with mediapla…

---

## [Nx and Whisper, "cannot build an empty tensor"](https://forum.elixirforum.com/t/nx-and-whisper-cannot-build-an-empty-tensor/62060)

<div class="topic-metadata">

**Author:** [@maz](https://forum.elixirforum.com/u/maz)\
**Replies:** 1\
**Last updated:** [March 4, 2024, 7:50pm UTC](https://forum.elixirforum.com/t/nx-and-whisper-cannot-build-an-empty-tensor/62060 "2024-03-04T19:50:51Z")

</div>

Using the live\_beats transcoding as a basis for this code, I’m transcribing an audio file. Sometimes, though, the very last segment will fail the entire batch run because it will attempt to transcribe silence. cannot bu…