Run accurate, fully local speech-to-text dictation in Unsloth Studio. Whisper Small provides better transcription quality than Tiny or Base while remaining practical for everyday local dictation.
Source du modèle
Description de la source
Run accurate, fully local speech-to-text dictation in Unsloth Studio. Whisper Small provides better transcription quality than Tiny or Base while remaining practical for everyday local dictation.
Sources
1 sourceVérifié 15 août
Artefacts du modèle
1 artefactExtraits de sources
2 extraitsThe model runs on your device through whisper.cpp. Your recorded audio does not need to be sent to a hosted transcription service.
whisper-small.bin: native F16 model for whisper.cppwhisper.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.
whisper-cli -m whisper-small.bin -f audio.wav
model.safetensors SHA-256: 1d7734884874f1a1513ed9aa760a4f8e97aaa02fd6d93a3a85d27b2ae9ca596bcfd85d74dc730828cef4e13ae65898d9dc6f695fd00394f4399f7310e73cf505ggml-org/whisper.cpp commit 080bbbe85230f624f0b52127f1ae1218247989f9The converted model was loaded by whisper.cpp and passed an end-to-end transcription test.
--- base_model: unslothai/whisper-small license: apache-2.0 library_name: whisper.cpp pipeline_tag: automatic-speech-recognition tags: - whisper - whisper.cpp - ggml - f16 - unsloth-studio - unsloth --- # Whisper Small F16 for Unsloth Studio Run accurate, fully local speech-to-text dictation in [Unsloth Studio](https://unsloth.ai/docs). Whisper Small provides better transcription quality than Tiny or Base while remaining practical for everyday local dictation. ## 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 Small**. 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-small.bin`: native F16 model for `whisper.cpp` - Download size: approximately 488 MB - Best for: improved accuracy with moderate local resource use `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-small.bin -f audio.wav ``` ## Integrity - Source `model.safetensors` SHA-256: `1d7734884874f1a1513ed9aa760a4f8e97aaa02fd6d93a3a85d27b2ae9ca596b` - Converted model SHA-256: `cfd85d74dc730828cef4e13ae65898d9dc6f695fd00394f4399f7310e73cf505` - Conversion tool: `ggml-org/whisper.cpp` commit `080bbbe85230f624f0b52127f1ae1218247989f9` The converted model was loaded by `whisper.cpp` and passed an end-to-end transcription test.
Source context: 0 downloads · 0 likes · Pipeline automatic-speech-recognition · Library whisper.cpp · Repo unslothai/whisper-small-GGUF