whisperfile / README.md
jartine's picture
Upload README.md
85874c5 verified
|
raw
history blame
1.84 kB
---
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),
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
```
![screenshot](screenshot.png)
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.