rust/delayed-streams-modeling
1
0
Fork 0
mirror of https://github.com/kyutai-labs/delayed-streams-modeling.git synced 2026-01-07 01:32:56 +00:00
Code Issues Packages Projects Releases Wiki Activity

Mention the pypi packages.

Browse Source
This commit is contained in:
laurent
2025-06-18 11:05:28 +02:00
parent cb1465c706
commit a783afd077
1 changed files with 5 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
README.md
View File

@@ -12,6 +12,8 @@ The main model handles english only, it has ~2.6b parameters.
<img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/> <img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/>
</a> </a>
This requires the [moshi package](https://pypi.org/project/moshi/)
with version 0.2.5 or later, which can be installed via pip.
```bash ```bash
# wget https://github.com/metavoiceio/metavoice-src/raw/main/assets/bria.mp3 # wget https://github.com/metavoiceio/metavoice-src/raw/main/assets/bria.mp3
@@ -21,6 +23,9 @@ python -m moshi.run_inference --hf-repo kyutai/stt-2.6b-en bria.mp3
#### MLX implementation #### MLX implementation
[[Hugging Face]](https://huggingface.co/kyutai/stt-2.6b-en-mlx) [[Hugging Face]](https://huggingface.co/kyutai/stt-2.6b-en-mlx)
This requires the [moshi-mlx package](https://pypi.org/project/moshi-mlx/)
with version 0.2.5 or later, which can be installed via pip.
```bash ```bash
# wget https://github.com/metavoiceio/metavoice-src/raw/main/assets/bria.mp3 # wget https://github.com/metavoiceio/metavoice-src/raw/main/assets/bria.mp3
python -m moshi_mlx.run_inference --hf-repo kyutai/stt-2.6b-en-mlx bria.mp3 --temp 0 python -m moshi_mlx.run_inference --hf-repo kyutai/stt-2.6b-en-mlx bria.mp3 --temp 0