Skip to content

Open-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving.

Refresh full ModelScope core links (#3363)

zhifu gao17c943a3c59b
diff --git a/model_zoo/modelscope_models.md b/model_zoo/modelscope_models.md
index cb2e354f3..d8966b289 100644
--- a/model_zoo/modelscope_models.md
+++ b/model_zoo/modelscope_models.md
@@ -16,14 +16,14 @@ Here we provided several pretrained models on different datasets. The details of
| Model Name | Language | Training Data | Vocab Size | Parameter | Offline/Online | Notes |
|:--------------------------------------------------------------------------------------------------------------------------------------------------:|:--------:|:--------------------------------:|:----------:|:---------:|:--------------:|:--------------------------------------------------------------------------------------------------------------------------------|
-| [Paraformer-large](https://www.modelscope.cn/models/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/summary) | CN & EN | Alibaba Speech Data (60000hours) | 8404 | 220M | Offline | Duration of input wav <= 20s |
+| [Paraformer-large](https://www.modelscope.cn/models/iic/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/summary) | CN & EN | Alibaba Speech Data (60000hours) | 8404 | 220M | Offline | Duration of input wav <= 20s |
| [Paraformer-large-long](https://www.modelscope.cn/models/iic/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch/summary) | CN & EN | Alibaba Speech Data (60000hours) | 8404 | 220M | Offline | Which would deal with arbitrary length input wav |
| [Paraformer-large-en-long](https://www.modelscope.cn/models/damo/speech_paraformer-large-vad-punc_asr_nat-en-16k-common-vocab10020/summary) | EN | Alibaba Speech Data (50000hours) | 10020 | 220M | Offline | Which would deal with arbitrary length input wav |
| [Paraformer-large-Spk](https://modelscope.cn/models/damo/speech_paraformer-large-vad-punc-spk_asr_nat-zh-cn/summary) | CN & EN | Alibaba Speech Data (60000hours) | 8404 | 220M | Offline | Supporting speaker diarizatioin for ASR results based on paraformer-large-long |
| [Paraformer-large-contextual](https://www.modelscope.cn/models/damo/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404/summary) | CN & EN | Alibaba Speech Data (60000hours) | 8404 | 220M | Offline | Which supports the hotword customization based on the incentive enhancement, and improves the recall and precision of hotwords. |
| [Paraformer](https://modelscope.cn/models/damo/speech_paraformer_asr_nat-zh-cn-16k-common-vocab8358-tensorflow1/summary) | CN & EN | Alibaba Speech Data (50000hours) | 8358 | 68M | Offline | Duration of input wav <= 20s |
| [Paraformer-online](https://www.modelscope.cn/models/damo/speech_paraformer_asr_nat-zh-cn-16k-common-vocab8404-online/summary) | CN & EN | Alibaba Speech Data (50000hours) | 8404 | 68M | Online | Which could deal with streaming input |
-| [Paraformer-large-online](https://www.modelscope.cn/models/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online/summary) | CN & EN | Alibaba Speech Data (60000hours) | 8404 | 220M | Online | Which could deal with streaming input |
+| [Paraformer-large-online](https://www.modelscope.cn/models/iic/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online/summary) | CN & EN | Alibaba Speech Data (60000hours) | 8404 | 220M | Online | Which could deal with streaming input |
| [Paraformer-tiny](https://www.modelscope.cn/models/damo/speech_paraformer-tiny-commandword_asr_nat-zh-cn-16k-vocab544-pytorch/summary) | CN | Alibaba Speech Data (200hours) | 544 | 5.2M | Offline | Lightweight Paraformer model which supports Mandarin command words recognition |
| [Paraformer-aishell](https://www.modelscope.cn/models/damo/speech_paraformer_asr_nat-aishell1-pytorch/summary) | CN | AISHELL (178hours) | 4234 | 43M | Offline | |
| [ParaformerBert-aishell](https://modelscope.cn/models/damo/speech_paraformerbert_asr_nat-zh-cn-16k-aishell1-vocab4234-pytorch/summary) | CN | AISHELL (178hours) | 4234 | 43M | Offline | |
@@ -75,14 +75,14 @@ Here we provided several pretrained models on different datasets. The details of
| Model Name | Training Data | Parameters | Sampling Rate | Notes |
|:----------------------------------------------------------------------------------------------:|:----------------------------:|:----------:|:-------------:|:------|
-| [FSMN-VAD](https://modelscope.cn/models/damo/speech_fsmn_vad_zh-cn-16k-common-pytorch/summary) | Alibaba Speech Data (5000hours) | 0.4M | 16000 | |
+| [FSMN-VAD](https://modelscope.cn/models/iic/speech_fsmn_vad_zh-cn-16k-common-pytorch/summary) | Alibaba Speech Data (5000hours) | 0.4M | 16000 | |
| [FSMN-VAD](https://modelscope.cn/models/damo/speech_fsmn_vad_zh-cn-8k-common/summary) | Alibaba Speech Data (5000hours) | 0.4M | 8000 | |
### Punctuation Restoration
| Model Name | Language | Training Data | Parameters | Vocab Size| Offline/Online | Notes |
|:--------------------------------------------------------------------------------------------------------------------------:|:---------|:----------------------------:|:----------:|:----------:|:--------------:|:------|
-| [CT-Transformer-Large](https://modelscope.cn/models/damo/punc_ct-transformer_cn-en-common-vocab471067-large/summary) | CN & EN | Alibaba Text Data(100M) | 1.1G | 471067 | Offline | large offline punctuation model |
+| [CT-Transformer-Large](https://modelscope.cn/models/iic/punc_ct-transformer_cn-en-common-vocab471067-large/summary) | CN & EN | Alibaba Text Data(100M) | 1.1G | 471067 | Offline | large offline punctuation model |
| [CT-Transformer](https://modelscope.cn/models/damo/punc_ct-transformer_zh-cn-common-vocab272727-pytorch/summary) | CN & EN | Alibaba Text Data(70M) | 291M | 272727 | Offline | offline punctuation model |
| [CT-Transformer-Realtime](https://modelscope.cn/models/damo/punc_ct-transformer_zh-cn-common-vad_realtime-vocab272727/summary) | CN & EN | Alibaba Text Data(70M) | 288M | 272727 | Online | online punctuation model |
diff --git a/model_zoo/modelscope_models_zh.md b/model_zoo/modelscope_models_zh.md
index 9dccebb44..2a2ddfa20 100644
--- a/model_zoo/modelscope_models_zh.md
+++ b/model_zoo/modelscope_models_zh.md
@@ -16,14 +16,14 @@
| 模型名字 | 语言 | 训练数据 | 词典大小 | 参数量 | 非实时/实时 | 备注 |
|:--------------------------------------------------------------------------------------------------------------------------------------------------:|:--------:|:---------------------:|:-----------------:|:----:|:-------:|:---------------------------|
-| [Paraformer-large](https://www.modelscope.cn/models/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/summary) | 中文和英文 | 阿里巴巴语音数据(60000小时) | 8404 | 220M | 非实时 | 输入wav文件持续时间不超过20秒 |
+| [Paraformer-large](https://www.modelscope.cn/models/iic/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/summary) | 中文和英文 | 阿里巴巴语音数据(60000小时) | 8404 | 220M | 非实时 | 输入wav文件持续时间不超过20秒 |
| [Paraformer-large长音频版本](https://www.modelscope.cn/models/iic/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch/summary) | 中文和英文 | 阿里巴巴语音数据(60000小时) | 8404 | 220M | 非实时 | 能够处理任意长度的输入wav文件 |
| [Paraformer-large-en长音频版本](https://www.modelscope.cn/models/damo/speech_paraformer-large-vad-punc_asr_nat-en-16k-common-vocab10020/summary) | 英文 | 阿里巴巴语音数据(50000小时) | 10020 | 220M | 非实时 | 能够处理任意长度的输入wav文件 |
| [Paraformer-large-Spk](https://modelscope.cn/models/damo/speech_paraformer-large-vad-punc-spk_asr_nat-zh-cn/summary) | 中文和英文 | 阿里巴巴语音数据(60000小时) | 8404 | 220M | 非实时 | 在长音频功能的基础上添加说话人识别功能 |
| [Paraformer-large热词](https://www.modelscope.cn/models/damo/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404/summary) | 中文和英文 | 阿里巴巴语音数据(60000小时) | 8404 | 220M | 非实时 | 基于激励增强的热词定制支持,可以提高热词的召回率和准确率,输入wav文件持续时间不超过20秒 |
| [Paraformer](https://modelscope.cn/models/damo/speech_paraformer_asr_nat-zh-cn-16k-common-vocab8358-tensorflow1/summary) | 中文和英文 | 阿里巴巴语音数据(50000小时) | 8358 | 68M | 离线 | 输入wav文件持续时间不超过20秒 |
| [Paraformer实时](https://modelscope.cn/models/damo/speech_paraformer_asr_nat-zh-cn-16k-common-vocab8404-online/summary) | 中文和英文 | 阿里巴巴语音数据 (50000hours) | 8404 | 68M | 实时 | 能够处理流式输入 |
-| [Paraformer-large实时](https://modelscope.cn/models/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online/summary) | 中文和英文 | 阿里巴巴语音数据 (60000hours) | 8404 | 220M | 实时 | 能够处理流式输入 |
+| [Paraformer-large实时](https://modelscope.cn/models/iic/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online/summary) | 中文和英文 | 阿里巴巴语音数据 (60000hours) | 8404 | 220M | 实时 | 能够处理流式输入 |
| [Paraformer-tiny](https://www.modelscope.cn/models/damo/speech_paraformer-tiny-commandword_asr_nat-zh-cn-16k-vocab544-pytorch/summary) | 中文 | 阿里巴巴语音数据 (200hours) | 544 | 5.2M | 非实时 | 轻量级Paraformer模型,支持普通话命令词识别 |
| [Paraformer-aishell](https://www.modelscope.cn/models/damo/speech_paraformer_asr_nat-aishell1-pytorch/summary) | 中文 | AISHELL (178hours) | 4234 | 43M | 非实时 | 学术模型 |
| [ParaformerBert-aishell](https://modelscope.cn/models/damo/speech_paraformerbert_asr_nat-zh-cn-16k-aishell1-vocab4234-pytorch/summary) | 中文 | AISHELL (178hours) | 4234 | 43M | 非实时 | 学术模型 |
@@ -80,14 +80,14 @@
| 模型名字 | 训练数据 | 模型参数 | Sampling Rate | 备注 |
|:----------------------------------------------------------------------------------------------:|:----------------------------:|:----------:|:-------------:|:------|
-| [FSMN-VAD](https://modelscope.cn/models/damo/speech_fsmn_vad_zh-cn-16k-common-pytorch/summary) | 阿里巴巴语音数据 (5000hours) | 0.4M | 16000 | |
+| [FSMN-VAD](https://modelscope.cn/models/iic/speech_fsmn_vad_zh-cn-16k-common-pytorch/summary) | 阿里巴巴语音数据 (5000hours) | 0.4M | 16000 | |
| [FSMN-VAD](https://modelscope.cn/models/damo/speech_fsmn_vad_zh-cn-8k-common/summary) | 阿里巴巴语音数据 (5000hours) | 0.4M | 8000 | |
### 标点恢复模型
| 模型名字 | 语言 | 训练数据 | 模型参数 | Vocab Size| 非实时/实时 | 备注 |
|:--------------------------------------------------------------------------------------------------------------------------:|:----------:|:----------------------------:|:----------:|:----------:|:--------------:|:--------|
-| [CT-Transformer-Large](https://modelscope.cn/models/damo/punc_ct-transformer_cn-en-common-vocab471067-large/summary) | 中文和英文 | Alibaba Text Data(100M) | 1.1G | 471067 | 非实时 | 支持中英文标点大模型 |
+| [CT-Transformer-Large](https://modelscope.cn/models/iic/punc_ct-transformer_cn-en-common-vocab471067-large/summary) | 中文和英文 | Alibaba Text Data(100M) | 1.1G | 471067 | 非实时 | 支持中英文标点大模型 |
| [CT-Transformer](https://modelscope.cn/models/damo/punc_ct-transformer_zh-cn-common-vocab272727-pytorch/summary) | 中文和英文 | Alibaba Text Data(70M) | 291M | 272727 | 非实时 | 支持中英文标点 |
| [CT-Transformer-Realtime](https://modelscope.cn/models/damo/punc_ct-transformer_zh-cn-common-vad_realtime-vocab272727/summary) | 中文和英文 | Alibaba Text Data(70M) | 288M | 272727 | 实时 | VAD点实时标点 |
diff --git a/tests/test_docs_funasr_install_commands.py b/tests/test_docs_funasr_install_commands.py
index 0091ed2e0..e208c5563 100644
--- a/tests/test_docs_funasr_install_commands.py
+++ b/tests/test_docs_funasr_install_commands.py
@@ -169,6 +169,32 @@ def test_model_zoo_tables_use_current_paraformer_modelscope_entry():
assert stale not in text
+def test_full_modelscope_tables_use_current_core_entries():
+ docs = [
+ (ROOT / "model_zoo/modelscope_models.md").read_text(),
+ (ROOT / "model_zoo/modelscope_models_zh.md").read_text(),
+ ]
+
+ current_entries = [
+ "models/iic/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/summary",
+ "models/iic/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online/summary",
+ "models/iic/punc_ct-transformer_cn-en-common-vocab471067-large/summary",
+ "models/iic/speech_fsmn_vad_zh-cn-16k-common-pytorch/summary",
+ ]
+ stale_entries = [
+ "models/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/summary",
+ "models/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online/summary",
+ "models/damo/punc_ct-transformer_cn-en-common-vocab471067-large/summary",
+ "models/damo/speech_fsmn_vad_zh-cn-16k-common-pytorch/summary",
+ ]
+
+ for text in docs:
+ for marker in current_entries:
+ assert marker in text
+ for marker in stale_entries:
+ assert marker not in text
+
+
def test_model_zoo_landing_tables_link_huggingface_repos():
docs = [
(