nikola/llama_cpp
1
0
Fork 0
Code Issues Pull Requests Actions 20 Packages Projects Releases Wiki Activity

tts : fix typos in README.md [no ci] (#19463)

Browse Source
This commit is contained in:
Daniel Bevenius
2026-02-10 07:30:41 +01:00
committed by GitHub
parent f0bfe54f55
commit 66d403c480
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tools/tts/README.md
+2 -2
View File
@@ -34,7 +34,7 @@ $ build/bin/llama-quantize models/outetts-0.2-0.5B-f16.gguf \
``` ```
The quantized model will be `models/outetts-0.2-0.5B-q8_0.gguf`. The quantized model will be `models/outetts-0.2-0.5B-q8_0.gguf`.
Next we do something simlar for the audio decoder. First download or checkout Next we do something similar for the audio decoder. First download or checkout
the model for the voice decoder: the model for the voice decoder:
```console ```console
$ pushd models $ pushd models
@@ -42,7 +42,7 @@ $ git clone --branch main --single-branch --depth 1 https://huggingface.co/novat
$ cd WavTokenizer-large-speech-75token && git lfs install && git lfs pull $ cd WavTokenizer-large-speech-75token && git lfs install && git lfs pull
$ popd $ popd
``` ```
This model file is PyTorch checkpoint (.ckpt) and we first need to convert it to This model file is a PyTorch checkpoint (.ckpt) and we first need to convert it to
huggingface format: huggingface format:
```console ```console
(venv) python tools/tts/convert_pt_to_hf.py \ (venv) python tools/tts/convert_pt_to_hf.py \