From 3fcdbc70b4a9d4299e1ecd0b5a1c35209f23fd69 Mon Sep 17 00:00:00 2001 From: SWivid Date: Sat, 9 Nov 2024 04:54:06 +0800 Subject: [PATCH] minor update --- README.md | 1 + src/f5_tts/infer/README.md | 2 +- src/f5_tts/infer/SHARED.md | 3 ++- 3 files changed, 4 insertions(+), 2 deletions(-) diff --git a/README.md b/README.md index 3802596..4e5fbd4 100644 --- a/README.md +++ b/README.md @@ -72,6 +72,7 @@ Currently supported features: - Basic TTS with Chunk Inference - Multi-Style / Multi-Speaker Generation - Voice Chat powered by Qwen2.5-3B-Instruct +- [Custom model](src/f5_tts/infer/SHARED.md) inference (local only) ```bash # Launch a Gradio app (web interface) diff --git a/src/f5_tts/infer/README.md b/src/f5_tts/infer/README.md index 783f235..cba4eb2 100644 --- a/src/f5_tts/infer/README.md +++ b/src/f5_tts/infer/README.md @@ -2,7 +2,7 @@ The pretrained model checkpoints can be reached at [🤗 Hugging Face](https://huggingface.co/SWivid/F5-TTS) and [🤖 Model Scope](https://www.modelscope.cn/models/SWivid/F5-TTS_Emilia-ZH-EN), or will be automatically downloaded when running inference scripts. -More checkpoints with whole community efforts can be found [here](src/f5_tts/infer/SHARED.md), supporting more languages. +**More checkpoints with whole community efforts can be found in [SHARED.md](SHARED.md), supporting more languages.** Currently support **30s for a single** generation, which is the **total length** including both prompt and output audio. However, you can provide `infer_cli` and `infer_gradio` with longer text, will automatically do chunk generation. Long reference audio will be **clip short to ~15s**. diff --git a/src/f5_tts/infer/SHARED.md b/src/f5_tts/infer/SHARED.md index f3c6ceb..881b519 100644 --- a/src/f5_tts/infer/SHARED.md +++ b/src/f5_tts/infer/SHARED.md @@ -4,6 +4,7 @@ - This document is serving as a quick lookup table for the community training/finetuning result, with various language support. - The models in this repository are open source and are based on voluntary contributions from contributors. - The use of models must be conditioned on respect for the respective creators. The convenience brought comes from their efforts. +- Welcome to pull request sharing your result here. @@ -25,7 +26,7 @@ MODEL_CKPT: hf://SWivid/F5-TTS/F5TTS_Base/model_1200000.safetensors VOCAB_FILE: hf://SWivid/F5-TTS/F5TTS_Base/vocab.txt ``` -***Other infos, e.g. Github Repo, Usage Instruction, Tutorial (Blog, Video, etc.) ...*** +*Other infos, e.g. Link to some sampled results, Github repo, Usage instruction, Tutorial (Blog, Video, etc.) ...* ### Mandarin