Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Added links to OPENVINO models #1978

Open
wants to merge 6 commits into
base: master
Choose a base branch
from
+16 −2
Open

Added links to OPENVINO models #1978

Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
d8b3a2c
Added linkd to OPENVINO models
twdragon Mar 20, 2024
a56f065
Typo fix
twdragon Mar 20, 2024
46ad5ba
Typo fix
twdragon Mar 20, 2024
0ce8d3b
Link added
twdragon Mar 20, 2024
b9966b7
Fixed wrong CID
twdragon Mar 20, 2024
ef6a638
Fixed wrong CID
twdragon Mar 21, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Jump to
Jump to file
Failed to load files.
Diff view
Diff view
18 changes: 16 additions & 2 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,9 +18,9 @@ High-performance inference of [OpenAI's Whisper](https://github.com/openai/whisp
- [4-bit and 5-bit integer quantization support](https://github.com/ggerganov/whisper.cpp#quantization)
- Zero memory allocations at runtime
- Support for CPU-only inference
- [Efficient GPU support for NVIDIA](https://github.com/ggerganov/whisper.cpp#nvidia-gpu-support-via-cublas)
- [Efficient GPU support for NVIDIA](./README.md#nvidia-gpu-support-via-cublas)
- [Partial OpenCL GPU support via CLBlast](https://github.com/ggerganov/whisper.cpp#opencl-gpu-support-via-clblast)
- [OpenVINO Support](https://github.com/ggerganov/whisper.cpp#openvino-support)
- [OpenVINO Support](./README.md#openvino-support)
- [C-style API](https://github.com/ggerganov/whisper.cpp/blob/master/whisper.h)

Supported platforms:
Expand Down Expand Up @@ -407,6 +407,20 @@ This can result in significant speedup in encoder performance. Here are the inst
The first time run on an OpenVINO device is slow, since the OpenVINO framework will compile the IR (Intermediate Representation) model to a device-specific 'blob'. This device-specific blob will get
cached for the next run.

### OpenVINO pre-generated models
The pre-generated models are being tested and prepared for upload to Huggingface (see [#1893](https://github.com/ggerganov/whisper.cpp/issues/1893)). For now, the models are available in the following IPFS folders:

|Model index|[IPFS CID](https://docs.ipfs.tech/concepts/content-addressing/)|HTTP Link|
|------------------|-----|---------------|
|`tiny`|`bafybeiba7jggi3qjhxaibz6x2lj7yyodfmu3c73wam5audas4vfiyonraq`|[Download](https://bafybeiba7jggi3qjhxaibz6x2lj7yyodfmu3c73wam5audas4vfiyonraq.ipfs.dweb.link)|
|`base`|`bafybeidxae4d7boax6qk3qjpeodi64zp6dyxh5mrqtvroah3e54jh3w3hq`|[Download](https://bafybeidxae4d7boax6qk3qjpeodi64zp6dyxh5mrqtvroah3e54jh3w3hq.ipfs.dweb.link/)|
|`small`|`bafybeiam4oa6re22vlxwylq5xfipxwudwzbeo7jyclvayvkdvwn2riqw3m`|[Download](https://bafybeiam4oa6re22vlxwylq5xfipxwudwzbeo7jyclvayvkdvwn2riqw3m.ipfs.dweb.link/)|
|`medium`|`bafybeibywkcnezurmnvmikf2sungw6fz3wmq32uimoq34mcgk3weqgq7mu`|[Download](https://bafybeibywkcnezurmnvmikf2sungw6fz3wmq32uimoq34mcgk3weqgq7mu.ipfs.dweb.link/)|
|`large`|`bafybeifatliqdfrvqlywiiiomxsa6qjprzb7fex4qfdr4cfiyt3nmcv6ri`|[Donwload](https://bafybeifatliqdfrvqlywiiiomxsa6qjprzb7fex4qfdr4cfiyt3nmcv6ri.ipfs.dweb.link)|
|`whisper-original`|`bafybeifiqguwimjqwhufoasmq75oyezvy2ylb6hu2evwlyqar6cvq7cjxy`|[Download](https://bafybeifiqguwimjqwhufoasmq75oyezvy2ylb6hu2evwlyqar6cvq7cjxy.ipfs.dweb.link)|

The download links are generated over [dweb.link](https://dweb.link). For download any other available IPFS-HTTP gateway could be used to download.

For more information about the Core ML implementation please refer to PR [#1037](https://github.com/ggerganov/whisper.cpp/pull/1037).

## NVIDIA GPU support
Expand Down