Skip to content
ModelListedExternal
Download

Whisper Base GGUF

Run fast, fully local speech-to-text dictation in Unsloth Studio. Whisper Base is a lightweight step up from Tiny and is a strong default when you want quick local dictation with better transcription quality.

Sourcehuggingface.co/unslothai/whisper-base-GGUF/tree/5599157ba4f91e0e091c328ec7de8446ce159c2e
KindOtherBase modelunslothai/whisper-baseVersionWhisper baseCgrade

Model source

Kind
Other
File size
141 MB
Base model
unslothai/whisper-base
Version
vWhisper base
Updated
Oct 31, 2026
Source
Hugging Face

Source description

Whisper Base F16 for Unsloth Studio

Run fast, fully local speech-to-text dictation in Unsloth Studio. Whisper Base is a lightweight step up from Tiny and is a strong default when you want quick local dictation with better transcription quality.

Run in Unsloth Studio

  1. Install or update Unsloth Studio.
  2. Open Settings > Voice.
  3. Open the local dictation model picker and select Whisper Base.
  4. Let Studio download and cache the model.
  5. Use the microphone button in the chat composer to dictate locally.

The model runs on your device through whisper.cpp. Your recorded audio does not need to be sent to a hosted transcription service.

Model file

  • whisper-base.bin: native F16 model for whisper.cpp
  • Download size: approximately 148 MB
  • Best for: a lightweight balance of speed and transcription quality

whisper.cpp uses a custom GGML binary format for Whisper. The model file is therefore named .bin, not .gguf, even though this repository follows the common -GGUF repository naming convention.

No low-bit quantization was applied. Matrix weights are stored as F16, while tensors that whisper.cpp requires in F32 remain F32.

Manual whisper.cpp usage

whisper-cli -m whisper-base.bin -f audio.wav

Integrity

  • Source model.safetensors SHA-256: 07cadb9f25677c8d50df603e66a98fbd842cce45047139baeb16e6219a1e807b
  • Converted model SHA-256: c2dad44135a48bc7c5a93564f4cd5cc8735ba8822999e358eb31f28d14d72a8b
  • Conversion tool: ggml-org/whisper.cpp commit 080bbbe85230f624f0b52127f1ae1218247989f9

The converted model was loaded by whisper.cpp and passed an end-to-end transcription test.

Sources

1 source
Hugging FacePrimaryVersion 5599157ba4f91e0e091c328ec7de8446ce159c2e
huggingface.co/unslothai/whisper-base-GGUF/tree/5599157ba4f91e0e091c328ec7de8446ce159c2e

Verified Oct 31

Model artifacts

1 artifact

whisper-base.bin

bin · 141 MB · SHA-256 c2dad44135a4…2a8b · Hugging Face

Download file

Source excerpts

2 excerpts
ReadmeAug 15huggingface.co/unslothai/whisper-base-GGUF

--- base_model: unslothai/whisper-base license: apache-2.0 library_name: whisper.cpp pipeline_tag: automatic-speech-recognition tags: - whisper - whisper.cpp - ggml - f16 - unsloth-studio - unsloth --- # Whisper Base F16 for Unsloth Studio Run fast, fully local speech-to-text dictation in [Unsloth Studio](https://unsloth.ai/docs). Whisper Base is a lightweight step up from Tiny and is a strong default when you want quick local dictation with better transcription quality. ## Run in Unsloth Studio 1. Install or update [Unsloth Studio](https://unsloth.ai/docs). 2. Open **Settings > Voice**. 3. Open the local dictation model picker and select **Whisper Base**. 4. Let Studio download and cache the model. 5. Use the microphone button in the chat composer to dictate locally. The model runs on your device through `whisper.cpp`. Your recorded audio does not need to be sent to a hosted transcription service. ## Model file - `whisper-base.bin`: native F16 model for `whisper.cpp` - Download size: approximately 148 MB - Best for: a lightweight balance of speed and transcription quality `whisper.cpp` uses a custom GGML binary format for Whisper. The model file is therefore named `.bin`, not `.gguf`, even though this repository follows the common `-GGUF` repository naming convention. No low-bit quantization was applied. Matrix weights are stored as F16, while tensors that `whisper.cpp` requires in F32 remain F32. ## Manual whisper.cpp usage ```bash whisper-cli -m whisper-base.bin -f audio.wav ``` ## Integrity - Source `model.safetensors` SHA-256: `07cadb9f25677c8d50df603e66a98fbd842cce45047139baeb16e6219a1e807b` - Converted model SHA-256: `c2dad44135a48bc7c5a93564f4cd5cc8735ba8822999e358eb31f28d14d72a8b` - Conversion tool: `ggml-org/whisper.cpp` commit `080bbbe85230f624f0b52127f1ae1218247989f9` The converted model was loaded by `whisper.cpp` and passed an end-to-end transcription test.

NoteAug 15huggingface.co/unslothai/whisper-base-GGUF

Source context: 0 downloads · 0 likes · Pipeline automatic-speech-recognition · Library whisper.cpp · Repo unslothai/whisper-base-GGUF