|
--- |
|
license: apache-2.0 |
|
license_link: LICENSE |
|
tags: |
|
- llamafile |
|
--- |
|
|
|
# OpenAI Whisper - llamafile |
|
|
|
Whisperfile is a high-performance implementation of [OpenAI's |
|
Whisper](https://github.com/openai/whisper) created by Mozilla Ocho as |
|
part of the [llamafile](https://github.com/Mozilla-Ocho/llamafile) |
|
project, based on the |
|
[whisper.cpp](https://github.com/ggerganov/whisper.cpp) software written |
|
by Georgi Gerganov, et al. |
|
|
|
- Model creator: [OpenAI](https://huggingface.co/collections/openai/whisper-release-6501bba2cf999715fd953013) |
|
- Original models: [openai/whisper-release](https://huggingface.co/collections/openai/whisper-release-6501bba2cf999715fd953013) |
|
- Origin of quantized weights: [ggerganov/whisper.cpp](https://huggingface.co/ggerganov/whisper.cpp) |
|
|
|
The model is packaged into executable weights, which we call |
|
[whisperfiles](https://github.com/Mozilla-Ocho/llamafile/blob/0.8.13/whisper.cpp/doc/index.md). |
|
This makes it easy to use the model on Linux, MacOS, Windows, FreeBSD, |
|
OpenBSD, and NetBSD for AMD64 and ARM64. |
|
|
|
## Quickstart |
|
|
|
Running the following on a desktop OS will transcribe the speech of a |
|
wav file into colorful text. |
|
|
|
``` |
|
wget https://huggingface.co/Mozilla/whisperfile/resolve/main/whisper-tiny.en.llamafile |
|
wget https://huggingface.co/Mozilla/whisperfile/resolve/main/raven_poe_64kb.wav |
|
chmod +x whisper-tiny.en.llamafile |
|
./whisper-tiny.en.llamafile -f raven_poe_64kb.wav -pc |
|
``` |
|
|
|
 |
|
|
|
There's also an HTTP server available: |
|
|
|
``` |
|
./whisper-tiny.en.llamafile --server |
|
``` |
|
|
|
Having **trouble?** See the ["Gotchas" |
|
section](https://github.com/mozilla-ocho/llamafile/?tab=readme-ov-file#gotchas) |
|
of the llamafile README. |
|
|
|
## Documentation |
|
|
|
See the [whisperfile |
|
documentation](https://github.com/Mozilla-Ocho/llamafile/blob/0.8.13/whisper.cpp/doc/index.md) |
|
for tutorials and further details. |
|
|
