WIlfLin commited on
Commit
7e5ed85
·
verified ·
1 Parent(s): 99de2e5

Clarify Qwen3-ASR Chinese and mixed-language postprocessing focus

Browse files
Files changed (1) hide show
  1. README.md +5 -2
README.md CHANGED
@@ -11,6 +11,8 @@ pipeline_tag: text-generation
11
  tags:
12
  - transcript-normalization
13
  - chinese
 
 
14
  - full-finetuning
15
  - numbered-lists
16
  - numeric-normalization
@@ -18,11 +20,12 @@ tags:
18
 
19
  # S1-mini-Chinese
20
 
21
- **这是在中文口语整理数据集上继续微调的 S1-mini 版本。**
 
22
  本模型基于 **S1-mini** by **Superwhisper**,保留原始模型名称、作者署名、`LICENSE` 和 `NOTICE`。
23
  当前版本是 **format-numbers-v5(2026-11-05)**,与目前部署的 BF16 权重一致。
24
 
25
- Chinese-data continued full fine-tuning of **S1-mini** by **Superwhisper** for speech-transcript normalization. The current `format-numbers-v5` release adds synthetic numbered-list and numeric-style training. This is a text postprocessor, not a speech recognizer.
26
 
27
  ## 当前版本的改动
28
 
 
11
  tags:
12
  - transcript-normalization
13
  - chinese
14
+ - qwen3-asr
15
+ - code-switching
16
  - full-finetuning
17
  - numbered-lists
18
  - numeric-normalization
 
20
 
21
  # S1-mini-Chinese
22
 
23
+ **本模型专门面向 Qwen3-ASR 的中文及中英混合转写后处理优化。**
24
+ 这是在中文口语整理数据集上继续微调的 S1-mini 版本。
25
  本模型基于 **S1-mini** by **Superwhisper**,保留原始模型名称、作者署名、`LICENSE` 和 `NOTICE`。
26
  当前版本是 **format-numbers-v5(2026-11-05)**,与目前部署的 BF16 权重一致。
27
 
28
+ Chinese-data continued full fine-tuning of **S1-mini** by **Superwhisper**, optimized for postprocessing Qwen3-ASR transcripts in Chinese and mixed Chinese/English. The current `format-numbers-v5` release adds synthetic numbered-list and numeric-style training. This is a text postprocessor, not a speech recognizer.
29
 
30
  ## 当前版本的改动
31