Fix links in README and update model references in SHARED.md; clean up imports in utils_infer.py

Author: sarpba

src/f5_tts/infer/README.md

@@ -24,7 +24,7 @@ Currently supported features:
 - Basic TTS with Chunk Inference
 - Multi-Style / Multi-Speaker Generation
 - Voice Chat powered by Qwen2.5-3B-Instruct
-- [Custom inference with more language support](src/f5_tts/infer/SHARED.md)
+- [Custom inference with more language support](SHARED.md)
 
 The cli command `f5-tts_infer-gradio` equals to `python src/f5_tts/infer/infer_gradio.py`, which launches a Gradio APP (web interface) for inference.
 

src/f5_tts/infer/SHARED.md

@@ -137,11 +137,11 @@ Config: {"dim": 1024, "depth": 22, "heads": 16, "ff_mult": 2, "text_dim": 512, "
 #### F5-TTS Base @ ja @ Jmica
 |Model|🤗Hugging Face|Data (Hours)|Model License|
 |:---:|:------------:|:-----------:|:-------------:|
-|F5-TTS Base|[ckpt & vocab](https://huggingface.co/Jmica/F5TTS/tree/main/JA_25498980)|[Emilia 1.7k JA](https://huggingface.co/datasets/amphion/Emilia-Dataset/tree/fc71e07) & [Galgame Dataset 5.4k](https://huggingface.co/datasets/OOPPEENN/Galgame_Dataset)|cc-by-nc-4.0|
+|F5-TTS Base|[ckpt & vocab](https://huggingface.co/Jmica/F5TTS/tree/main/JA_21999120)|[Emilia 1.7k JA](https://huggingface.co/datasets/amphion/Emilia-Dataset/tree/fc71e07) & [Galgame Dataset 5.4k](https://huggingface.co/datasets/OOPPEENN/Galgame_Dataset)|cc-by-nc-4.0|
 
 ```bash
-Model: hf://Jmica/F5TTS/JA_25498980/model_25498980.pt
-Vocab: hf://Jmica/F5TTS/JA_25498980/vocab_updated.txt
+Model: hf://Jmica/F5TTS/JA_21999120/model_21999120.pt
+Vocab: hf://Jmica/F5TTS/JA_21999120/vocab_japanese.txt
 Config: {"dim": 1024, "depth": 22, "heads": 16, "ff_mult": 2, "text_dim": 512, "text_mask_padding": False, "conv_layers": 4, "pe_attn_head": 1}
 ```
 

src/f5_tts/infer/utils_infer.py

@@ -21,7 +21,7 @@
 import torch
 import torchaudio
 import tqdm
-from huggingface_hub import snapshot_download, hf_hub_download
+from huggingface_hub import hf_hub_download
 from pydub import AudioSegment, silence
 from transformers import pipeline
 from vocos import Vocos
@@ -128,11 +128,12 @@ def load_vocoder(vocoder_name="vocos", is_local=False, local_path="", device=dev
         except ImportError:
             print("You need to follow the README to init submodule and change the BigVGAN source code.")
         if is_local:
-            """download from https://huggingface.co/nvidia/bigvgan_v2_24khz_100band_256x/tree/main"""
+            # download generator from https://huggingface.co/nvidia/bigvgan_v2_24khz_100band_256x/tree/main
             vocoder = bigvgan.BigVGAN.from_pretrained(local_path, use_cuda_kernel=False)
         else:
-            local_path = snapshot_download(repo_id="nvidia/bigvgan_v2_24khz_100band_256x", cache_dir=hf_cache_dir)
-            vocoder = bigvgan.BigVGAN.from_pretrained(local_path, use_cuda_kernel=False)
+            vocoder = bigvgan.BigVGAN.from_pretrained(
+                "nvidia/bigvgan_v2_24khz_100band_256x", use_cuda_kernel=False, cache_dir=hf_cache_dir
+            )
 
         vocoder.remove_weight_norm()
         vocoder = vocoder.eval().to(device)