tipi/kyutai
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Rename the repos.

Browse Source
This commit is contained in:
laurent 2025-06-17 10:28:47 +02:00
parent 1f482e5b8d
commit ad618fd64d
2 changed files with 8 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
README.md
View File

@ -7,23 +7,23 @@ Delayed Streams Modeling (DSM) is a flexible formulation for streaming, multimod
The leaderboard model handles english only, it has ~2.6B parameters.
#### PyTorch implementation
[[Hugging Face]](https://huggingface.co/kyutai/stt)
[[Hugging Face]](https://huggingface.co/kyutai/stt-2.6B-en)
```bash
# wget https://github.com/metavoiceio/metavoice-src/raw/main/assets/bria.mp3
python -m moshi.run_inference --hf-repo kyutai/stt bria.mp3
python -m moshi.run_inference --hf-repo kyutai/stt-2.6B-en bria.mp3
```
#### MLX implementation
[[Hugging Face]](https://huggingface.co/kyutai/stt-mlx)
[[Hugging Face]](https://huggingface.co/kyutai/stt-2.6B-en-mlx)
```bash
# wget https://github.com/metavoiceio/metavoice-src/raw/main/assets/bria.mp3
python -m moshi_mlx.run_inference --hf-repo kyutai/stt-mlx bria.mp3 --temp 0
python -m moshi_mlx.run_inference --hf-repo kyutai/stt-2.6B-en-mlx bria.mp3 --temp 0
```
#### Rust implementation
[[Hugging Face]](https://huggingface.co/kyutai/stt-candle)
[[Hugging Face]](https://huggingface.co/kyutai/stt-2.6B-en-candle)
The Rust implementation provides a server that can process multiple streaming
queries in parallel. Dependening on the amount of memory on your GPU, you may

6
configs/config-stt-hf.toml
View File

@ -6,9 +6,9 @@ authorized_ids = ["open_token"]
[modules.asr]
path = "/api/asr-streaming"
type = "BatchedAsr"
lm_model_file = "hf://kyutai/stt-candle/model.safetensors"
text_tokenizer_file = "hf://kyutai/stt-candle/tokenizer_en_audio_4000.model"
audio_tokenizer_file = "hf://kyutai/stt-candle/mimi-pytorch-e351c8d8@125.safetensors"
lm_model_file = "hf://kyutai/stt-2.6B-en-candle/model.safetensors"
text_tokenizer_file = "hf://kyutai/stt-2.6B-en-candle/tokenizer_en_audio_4000.model"
audio_tokenizer_file = "hf://kyutai/stt-2.6B-en-candle/mimi-pytorch-e351c8d8@125.safetensors"
asr_delay_in_tokens = 6
batch_size = 16
conditioning_learnt_padding = true