From 60f1b31446f948e12bfa7b6cafe8d405889fc3e2 Mon Sep 17 00:00:00 2001 From: unknown Date: Sat, 19 Oct 2024 11:29:59 +0300 Subject: [PATCH] update read me for new arg --- README.md | 3 +++ 1 file changed, 3 insertions(+) diff --git a/README.md b/README.md index 74e6621..bee0731 100644 --- a/README.md +++ b/README.md @@ -86,6 +86,9 @@ Currently support 30s for a single generation, which is the **TOTAL** length of Either you can specify everything in `inference-cli.toml` or override with flags. Leave `--ref_text ""` will have ASR model transcribe the reference audio automatically (use extra GPU memory). If encounter network error, consider use local ckpt, just set `ckpt_path` in `inference-cli.py` +for change model use --ckpt_file to specify the model you want to load, +for change vocab.txt use --vocab_file to provide your vocab.txt file. + ```bash python inference-cli.py \ --model "F5-TTS" \