Skip to content

add-kimi-audio-snippet #1429

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

Open
wants to merge 2 commits into
base: main
Choose a base branch
from
Open

add-kimi-audio-snippet #1429

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
a7706d3
add-kimi-audio-snippet
May 6, 2025
db4cb47
Update packages/tasks/src/model-libraries.ts
Wauplin May 6, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
31 changes: 31 additions & 0 deletions packages/tasks/src/model-libraries-snippets.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -561,6 +561,37 @@ export const keras_hub = (model: ModelData): string[] => {
return snippets;
};

export const kimi_audio = (model: ModelData): string[] => [
`# Example usage for KimiAudio
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Add a line here to install the library

Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

pip install ...

from kimia_infer.api.kimia import KimiAudio

model = KimiAudio(model_path="${model.id}", load_detokenizer=True)

sampling_params = {
"audio_temperature": 0.8,
"audio_top_k": 10,
"text_temperature": 0.0,
"text_top_k": 5,
}

# For ASR
asr_audio = "asr_example.wav"
messages_asr = [
{"role": "user", "message_type": "text", "content": "Please transcribe the following audio:"},
{"role": "user", "message_type": "audio", "content": asr_audio}
]
_, text = model.generate(messages_asr, **sampling_params, output_type="text")
print(text)

# For Q&A
qa_audio = "qa_example.wav"
messages_conv = [{"role": "user", "message_type": "audio", "content": qa_audio}]
wav, text = model.generate(messages_conv, **sampling_params, output_type="both")
sf.write("output_audio.wav", wav.cpu().view(-1).numpy(), 24000)
print(text)
`,
];

export const lightning_ir = (model: ModelData): string[] => {
if (model.tags.includes("bi-encoder")) {
return [
Expand Down
7 changes: 7 additions & 0 deletions packages/tasks/src/model-libraries.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -459,6 +459,13 @@ export const MODEL_LIBRARIES_UI_ELEMENTS = {
snippets: snippets.keras_hub,
filter: true,
},
"kimi-audio": {
prettyLabel: "KimiAudio",
repoName: "KimiAudio",
repoUrl: "https://github.com/MoonshotAI/Kimi-Audio",
snippets: snippets.kimi_audio,
filter: false,
},
k2: {
prettyLabel: "K2",
repoName: "k2",
Expand Down