From 5e6424e809d3d46ecd6701f472a1d8f4496aa9a1 Mon Sep 17 00:00:00 2001
From: Cherrytest <cherrytest@163.com>
Date: Tue, 26 Aug 2025 05:28:32 +0000
Subject: [PATCH] Upload folder using ModelScope SDK

---
 README.md                              | 57 +++++++-------------------
 configuration.json                     |  1 +
 wav2vec2-chinese-base_fp16.safetensors |  3 ++
 wav2vec2-chinese-base_fp32.safetensors |  3 ++
 4 files changed, 21 insertions(+), 43 deletions(-)
 create mode 100644 configuration.json
 create mode 100644 wav2vec2-chinese-base_fp16.safetensors
 create mode 100644 wav2vec2-chinese-base_fp32.safetensors

diff --git a/README.md b/README.md
index 66c636b..45aad62 100644
--- a/README.md
+++ b/README.md
@@ -1,47 +1,18 @@
 ---
-license: Apache License 2.0
-
-#model-type:
-##如 gpt、phi、llama、chatglm、baichuan 等
-#- gpt
-
-#domain:
-##如 nlp、cv、audio、multi-modal
-#- nlp
-
-#language:
-##语言代码列表 https://help.aliyun.com/document_detail/215387.html?spm=a2c4g.11186623.0.0.9f8d7467kni6Aa
-#- cn 
-
-#metrics:
-##如 CIDEr、Blue、ROUGE 等
-#- CIDEr
-
-#tags:
-##各种自定义，包括 pretrained、fine-tuned、instruction-tuned、RL-tuned 等训练方法和其他
-#- pretrained
-
-#tools:
-##如 vllm、fastchat、llamacpp、AdaSeq 等
-#- vllm
+license: mit
+base_model:
+- TencentGameMate/chinese-wav2vec2-base
 ---
-### 当前模型的贡献者未提供更加详细的模型介绍。模型文件和权重，可浏览“模型文件”页面获取。
-#### 您可以通过如下git clone命令，或者ModelScope SDK来下载模型
 
-SDK下载
-```bash
-#安装ModelScope
-pip install modelscope
-```
-```python
-#SDK模型下载
-from modelscope import snapshot_download
-model_dir = snapshot_download('Kijai/wav2vec2_safetensors')
-```
-Git下载
-```
-#Git模型下载
-git clone https://www.modelscope.cn/Kijai/wav2vec2_safetensors.git
-```
+https://huggingface.co/TencentGameMate/chinese-wav2vec2-base
 
-<p style="color: lightgrey;">如果您是本模型的贡献者，我们邀请您根据<a href="https://modelscope.cn/docs/ModelScope%E6%A8%A1%E5%9E%8B%E6%8E%A5%E5%85%A5%E6%B5%81%E7%A8%8B%E6%A6%82%E8%A7%88" style="color: lightgrey; text-decoration: underline;">模型贡献文档</a>，及时完善模型卡片内容。</p>
\ No newline at end of file
+in .safetensors format.
+
+Used in ComfyUI WanVideoWrapper for MultiTalk and InfiniteTalk
+
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/63297908f0b2fc94904a65b8/Fm4HM6arSliDi6acJNLoj.png)
+
+Example of instantiating the model and loading the weights from single file:
+
+https://github.com/kijai/ComfyUI-WanVideoWrapper/blob/main/multitalk/nodes.py
\ No newline at end of file
diff --git a/configuration.json b/configuration.json
new file mode 100644
index 0000000..159097f
--- /dev/null
+++ b/configuration.json
@@ -0,0 +1 @@
+{"framework": "pytorch", "task": "others", "allow_remote": true}
\ No newline at end of file
diff --git a/wav2vec2-chinese-base_fp16.safetensors b/wav2vec2-chinese-base_fp16.safetensors
new file mode 100644
index 0000000..195dbb8
--- /dev/null
+++ b/wav2vec2-chinese-base_fp16.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5d341613ef84828764d4e58310728d778a19ec532f887d93a13b67745f1cc81
+size 134
diff --git a/wav2vec2-chinese-base_fp32.safetensors b/wav2vec2-chinese-base_fp32.safetensors
new file mode 100644
index 0000000..2645812
--- /dev/null
+++ b/wav2vec2-chinese-base_fp32.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d8bde815fb5c9b56ab89571f3c248fd9fb7f92b1ba6a68bd4e9e5da129c7cb4
+size 134