diff options
| author | zachcp <zachcp@users.noreply.github.com> | 2024-11-18 08:19:23 -0500 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2024-11-18 14:19:23 +0100 |
| commit | 386fd8abb4be23c125e8100fed932f17d356a160 (patch) | |
| tree | d4964322db768d31e2e4c1949848315fcfd7cfa2 /candle-transformers/src/models/mimi/mod.rs | |
| parent | 12d7e7b1450f0c3f87c3cce3a2a1dd1674cb8fd7 (diff) | |
| download | candle-386fd8abb4be23c125e8100fed932f17d356a160.tar.gz candle-386fd8abb4be23c125e8100fed932f17d356a160.tar.bz2 candle-386fd8abb4be23c125e8100fed932f17d356a160.zip | |
Module Docs (#2624)
* update whisper
* update llama2c
* update t5
* update phi and t5
* add a blip model
* qlamma doc
* add two new docs
* add docs and emoji
* additional models
* openclip
* pixtral
* edits on the model docs
* update yu
* update a fe wmore models
* add persimmon
* add model-level doc
* names
* update module doc
* links in heira
* remove empty URL
* update more hyperlinks
* updated hyperlinks
* more links
* Update mod.rs
---------
Co-authored-by: Laurent Mazare <laurent.mazare@gmail.com>
Diffstat (limited to 'candle-transformers/src/models/mimi/mod.rs')
| -rw-r--r-- | candle-transformers/src/models/mimi/mod.rs | 24 |
1 files changed, 21 insertions, 3 deletions
diff --git a/candle-transformers/src/models/mimi/mod.rs b/candle-transformers/src/models/mimi/mod.rs index f19f9ae5..8945abfb 100644 --- a/candle-transformers/src/models/mimi/mod.rs +++ b/candle-transformers/src/models/mimi/mod.rs @@ -1,9 +1,27 @@ //! mimi model //! -//! Mimi is a state-of-the-art audio neural codec. +//! [Mimi](https://huggingface.co/kyutai/mimi) is a state of the art audio +//! compression model using an encoder/decoder architecture with residual vector +//! quantization. The candle implementation supports streaming meaning that it's +//! possible to encode or decode a stream of audio tokens on the flight to provide +//! low latency interaction with an audio model. //! -//! - [HuggingFace Model Card](https://huggingface.co/kyutai/mimi) -//! - [GitHub](https://github.com/kyutai-labs/moshi) +//! - 🤗 [HuggingFace Model Card](https://huggingface.co/kyutai/mimi) +//! - 💻 [GitHub](https://github.com/kyutai-labs/moshi) +//! +//! +//! # Example +//! ```bash +//! # Generating some audio tokens from an audio files. +//! wget https://github.com/metavoiceio/metavoice-src/raw/main/assets/bria.mp3 +//! cargo run --example mimi \ +//! --features mimi --release -- \ +//! audio-to-code bria.mp3 bria.safetensors +//! +//! # And decoding the audio tokens back into a sound file. +//! cargo run --example mimi +//! --features mimi --release -- \ +//! code-to-audio bria.safetensors bria.wav //! // Copyright (c) Kyutai, all rights reserved. |