Skip to content

Commit b3b1a91

Browse files
gujieyegujieye
committed
chore: update bailian-docs-llm-wiki (2026-10-05)
1 parent 477ae27 commit b3b1a91

94 files changed

Lines changed: 3969 additions & 4065 deletions

File tree

Some content is hidden

Large Commits have some content hidden by default. Use the searchbox below for content that may be hidden.

‎skills/bailian-docs-llm-wiki/llms.txt‎

Lines changed: 545 additions & 545 deletions
Large diffs are not rendered by default.

‎skills/bailian-docs-llm-wiki/models/families.jsonl‎

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -28,6 +28,7 @@
2828
{"slug":"glm-fast","name":"GLM-5.2-Fast","description":"GLM-5.2-Fast-Preview 是智谱 AI 旗舰模型 GLM-5.2 的高速版本，支持 1M 超长上下文，模型能力对齐 GLM-5.2 标准版，具备逻辑推理、长文本理解与代码生成能力。通过推理加速优化，输出 TPS 可达 GLM-5.2 标准版的 1.5～2 倍，显著提升输出速度，适用于实时对话、Agent 多轮调用、流式代码生成等对输出速度敏感的场景。","primaryCapability":"TG","capabilities":["TG"],"providers":["zhipu-ai"],"itemCount":1,"items":[{"model":"glm-5.2-fast-preview","name":"GLM-5.2-Fast-Preview","contextWindow":1000000,"capabilities":["TG"]}],"detailPath":"groups/glm-fast.json","maxContextWindow":1000000}
2929
{"slug":"gui-plus","name":"GUI-Plus","description":"GUI系列图形界面交互基础模型，针对手机端与电脑端图形界面理解与交互任务，性能优于开源版同类GUI模型。全面升级跨平台界面理解与多步任务规划，支持跨应用复杂任务；具备精细化动作执行与多角色多智能体协作能力，胜任真实复杂交互场景。","primaryCapability":"VU","capabilities":["VU"],"providers":["qwen-domain-model"],"itemCount":1,"items":[{"model":"gui-plus","name":"GUI-Plus","contextWindow":256000,"capabilities":["VU"]}],"detailPath":"groups/gui-plus.json","maxContextWindow":256000}
3030
{"slug":"gummy-chat-v1","name":"一句话识别及翻译V1.0","description":"多语言语音转写及翻译的多模态大模型。本模型支持60秒以内的实时语音识别，适用于语音搜索、设备指令等场景。提供10个混合语种的高准确率识别服务，同时支持中英日韩互译，以其他6个语种翻译成中文或英文。","primaryCapability":"ASR","capabilities":["ASR"],"providers":["qwen"],"itemCount":1,"items":[{"model":"gummy-chat-v1","name":"一句话识别及翻译V1.0","capabilities":["ASR"]}],"detailPath":"groups/gummy-chat-v1.json"}
31+
{"slug":"gummy-realtime-v1","name":"实时语音识别及翻译V1.0","description":"多语言语音转写及翻译的多模态大模型。本模型提供长时间、高准确率、实时转写中/英/日/韩等10个混合语种的服务。同时支持中英日韩互译，以其他6个语种翻译成中文或英文。","primaryCapability":"Realtime-Audio-Translate","capabilities":["Realtime-Audio-Translate"],"providers":["qwen"],"itemCount":1,"items":[{"model":"gummy-realtime-v1","name":"实时语音识别及翻译V1.0","capabilities":["Realtime-Audio-Translate"]}],"detailPath":"groups/gummy-realtime-v1.json"}
3132
{"slug":"happyhorse-1.0","name":"HappyHorse-1.0","description":"视频生成与编辑系列，支持文生、图生、参考生及自然语言视频编辑，适合常规创作和局部调整。","primaryCapability":"VG","capabilities":["VG"],"providers":["happyhorse"],"itemCount":4,"items":[{"model":"happyhorse-1.0-i2v","name":"HappyHorse-1.0-I2V","capabilities":["VG"]},{"model":"happyhorse-1.0-r2v","name":"HappyHorse-1.0-R2V","capabilities":["VG"]},{"model":"happyhorse-1.0-t2v","name":"HappyHorse-1.0-T2V","capabilities":["VG"]},{"model":"happyhorse-1.0-video-edit","name":"HappyHorse-1.0-Video-Edit","capabilities":["VG"]}],"detailPath":"groups/happyhorse-1.0.json"}
3233
{"slug":"happyhorse-1.1","name":"HappyHorse-1.1","description":"HappyHorse 新一代视频生成系列，支持文生、图生和参考生视频，全面提升画面质感、主体一致性和动态表现。","primaryCapability":"VG","capabilities":["VG"],"providers":["happyhorse"],"itemCount":3,"items":[{"model":"happyhorse-1.1-i2v","name":"HappyHorse-1.1-I2V","capabilities":["VG"]},{"model":"happyhorse-1.1-r2v","name":"HappyHorse-1.1-R2V","capabilities":["VG"]},{"model":"happyhorse-1.1-t2v","name":"HappyHorse-1.1-T2V","capabilities":["VG"]}],"detailPath":"groups/happyhorse-1.1.json"}
3334
{"slug":"happyoyster-1.0","name":"HappyOyster-1.0","description":"Happyoyster 系列首个实时交互的开放式世界模型。只需输入一句话，即可生成一个完整、可演绎、可探索、可互动的数字世界。","primaryCapability":"World-Model","capabilities":["World-Model"],"providers":["happyoyster"],"itemCount":1,"items":[{"model":"happyoyster-1.0-adventure","name":"HappyOyster-1.0-Adventure","capabilities":["World-Model"]}],"detailPath":"groups/happyoyster-1.0.json"}

‎skills/bailian-docs-llm-wiki/models/groups/gummy-realtime-v1.json‎

Lines changed: 67 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,67 @@
1+
{
2+
"name": "实时语音识别及翻译V1.0",
3+
"description": "多语言语音转写及翻译的多模态大模型。本模型提供长时间、高准确率、实时转写中/英/日/韩等10个混合语种的服务。同时支持中英日韩互译，以其他6个语种翻译成中文或英文。",
4+
"items": [
5+
{
6+
"inferenceMetadata": {
7+
"response_modality": [
8+
"Text"
9+
],
10+
"request_modality": [
11+
"Audio"
12+
]
13+
},
14+
"description": "多语言语音转写及翻译的多模态大模型。本模型提供长时间、高准确率、实时转写中/英/日/韩等10个混合语种的服务。同时支持中英日韩互译，以其他6个语种翻译成中文或英文。",
15+
"features": [],
16+
"provider": "qwen",
17+
"model": "gummy-realtime-v1",
18+
"prices": [
19+
{
20+
"priceUnit": "每秒",
21+
"price": "0.00015",
22+
"timeBand": "standard",
23+
"ntmAmountType": "duration",
24+
"type": "content_duration",
25+
"priceName": "音频时长"
26+
}
27+
],
28+
"qpmInfo": {
29+
"model-default-actual": {
30+
"count_limit_period": 1,
31+
"count_limit": 10,
32+
"type": "model-default"
33+
},
34+
"model-default": {
35+
"count_limit_period": 1,
36+
"count_limit": 10,
37+
"type": "model-default"
38+
}
39+
},
40+
"priceTimeBands": [
41+
"standard"
42+
],
43+
"capabilities": [
44+
"Realtime-Audio-Translate"
45+
],
46+
"versionTag": "MAJOR",
47+
"latestOnlineAt": "2025-03-04T04:07:10.000+00:00",
48+
"offlineInfo": {
49+
"inference": {
50+
"announceUrl": "https://www.aliyun.com/notice/118331",
51+
"offlineTime": "2026-10-10 00:00:00"
52+
}
53+
},
54+
"inferenceProvider": "aliyun-bailian",
55+
"name": "实时语音识别及翻译V1.0",
56+
"docUrl": "https://docs.bailian.console.aliyun.com/zh/model-studio/real-time-speech-recognition-and-translation-api-reference",
57+
"samples": {
58+
"dashscope": {
59+
"default": {
60+
"python": "import requests\nfrom http import HTTPStatus\n\nimport dashscope\nfrom dashscope.audio.asr import *\n\n# 若没有将API Key配置到环境变量中，需将your-api-key替换为自己的API Key\n# dashscope.api_key = \"your-api-key\"\n\nr = requests.get(\n \"https://dashscope.oss-cn-beijing.aliyuncs.com/samples/audio/paraformer/hello_world_female2.wav\"\n)\nwith open(\"asr_example.wav\", \"wb\") as f:\n f.write(r.content)\n\ntranslator = TranslationRecognizerRealtime(\n model=\"gummy-realtime-v1\",\n format=\"wav\",\n sample_rate=16000,\n translation_target_languages=[\"en\"],\n translation_enabled=True,\n callback=None,\n)\nresult = translator.call(\"asr_example.wav\")\nif not result.error_message:\n print(\"request id: \", result.request_id)\n print(\"transcription: \")\n for transcription_result in result.transcription_result_list:\n print(transcription_result.text)\n print(\"translation[en]: \")\n\n for translation_result in result.translation_result_list:\n print(translation_result.get_translation('en').text)\nelse:\n print(\"Error: \", result.error_message)",
61+
"java": "import com.alibaba.dashscope.audio.asr.translation.TranslationRecognizerParam;\nimport com.alibaba.dashscope.audio.asr.translation.TranslationRecognizerRealtime;\nimport com.alibaba.dashscope.audio.asr.translation.results.TranscriptionResult;\nimport com.alibaba.dashscope.audio.asr.translation.results.TranslationRecognizerResultPack;\nimport com.alibaba.dashscope.audio.asr.translation.results.TranslationResult;\n\nimport java.io.File;\nimport java.util.ArrayList;\n\npublic class Main {\n\n public static void main(String[] args) {\n String targetLanguage = \"en\";\n // 创建Recognition实例\n TranslationRecognizerRealtime translator = new TranslationRecognizerRealtime();\n // 创建RecognitionParam，请在实际使用中替换真实apiKey\n TranslationRecognizerParam param =\n TranslationRecognizerParam.builder()\n // 若没有将API Key配置到环境变量中，需将下面这行代码注释放开，并将your-api-key替换为自己的API Key\n // .apiKey(\"your-api-key\")\n .model(\"gummy-realtime-v1\")\n .format(\"wav\") // 'pcm'、'wav'、'mp3'、'opus'、'speex'、'aac'、'amr', you\n // can check the supported formats in the document\n .sampleRate(16000)\n .transcriptionEnabled(true)\n .sourceLanguage(\"auto\")\n .translationEnabled(true)\n .translationLanguages(new String[] {targetLanguage})\n .build();\n // 直接将结果保存到script.txt中\n TranslationRecognizerResultPack result = translator.call(param, new File(\"hello_world.wav\"));\n // 任务结束后关闭 websocket 连接\n translator.getDuplexApi().close(1000, \"bye\");\n if (result.getError() != null) {\n System.out.println(\"error: \" + result.getError());\n throw new RuntimeException(result.getError());\n } else {\n System.out.println(\"RequestId: \" + result.getRequestId());\n System.out.println(\"Transcription Results:\");\n ArrayList<TranscriptionResult> transcriptionResults = result.getTranscriptionResultList();\n for (int i = 0; i < transcriptionResults.size(); i++) {\n System.out.println(transcriptionResults.get(i).getText());\n }\n\n System.out.println(\"English Translation Results:\");\n ArrayList<TranslationResult> translationResultList = result.getTranslationResultList();\n for (int i = 0; i < translationResultList.size(); i++) {\n System.out.println(translationResultList.get(i).getTranslation(targetLanguage).getText());\n }\n }\n System.exit(0);\n }\n}"
62+
}
63+
}
64+
}
65+
}
66+
]
67+
}

‎skills/bailian-docs-llm-wiki/models/index.json‎

Lines changed: 21 additions & 6 deletions
Original file line numberDiff line numberDiff line change
@@ -1,9 +1,9 @@
11
{
2-
"updatedAt": "2026-10-04",
3-
"totalFamilies": 188,
4-
"totalModels": 434,
2+
"updatedAt": "2026-10-05",
3+
"totalFamilies": 189,
4+
"totalModels": 435,
55
"profileCoverage": {
6-
"full": 377,
6+
"full": 378,
77
"partial": 51,
88
"structured-only": 6,
99
"none": 0
@@ -19,7 +19,7 @@
1919
"Realtime-ASR": 8,
2020
"Multimodal-Omni": 7,
2121
"Realtime-Omni": 5,
22-
"Realtime-Audio-Translate": 3,
22+
"Realtime-Audio-Translate": 4,
2323
"ME": 2,
2424
"Realtime-Chatting": 2,
2525
"Realtime-Text-to-Speech": 2,
@@ -28,7 +28,7 @@
2828
"3D-generation": 1
2929
},
3030
"providerDistribution": {
31-
"qwen": 116,
31+
"qwen": 117,
3232
"qwen-domain-model": 36,
3333
"wan": 14,
3434
"mini-max": 4,
@@ -552,6 +552,21 @@
552552
"gummy-chat-v1"
553553
]
554554
},
555+
{
556+
"slug": "gummy-realtime-v1",
557+
"name": "实时语音识别及翻译V1.0",
558+
"primaryCapability": "Realtime-Audio-Translate",
559+
"capabilities": [
560+
"Realtime-Audio-Translate"
561+
],
562+
"providers": [
563+
"qwen"
564+
],
565+
"itemCount": 1,
566+
"items": [
567+
"gummy-realtime-v1"
568+
]
569+
},
555570
{
556571
"slug": "happyhorse-1.0",
557572
"name": "HappyHorse-1.0",

‎skills/bailian-docs-llm-wiki/models/index.md‎

Lines changed: 4 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -1,6 +1,6 @@
11
# 百炼模型市场索引
22

3-
> 自动生成 · 共 188 个模型家族 · 434 个主干模型 · 更新于 2026-10-04
3+
> 自动生成 · 共 189 个模型家族 · 435 个主干模型 · 更新于 2026-10-05
44
55
**机器查询走结构化文件**：
66

@@ -397,14 +397,16 @@ join：`models.jsonl[].family == families.jsonl[].slug == index.json.families[].
397397
- [Qwen3.8-Omni-Flash-Realtime](groups/qwen3.8-omni-flash-realtime.json) — Qwen3.8-Omni-Flash-Realtime 通过多种实时协议提供音视频双工交互，面向智能硬件、机器人与实时交互 Agent。支持多通道音频输入与多种通道布局，视频表征可在细粒度与聚合之间按…
398398
- 模型：`qwen3.8-omni-flash-realtime`
399399

400-
## 实时音频翻译 `Realtime-Audio-Translate` — 3 个家族
400+
## 实时音频翻译 `Realtime-Audio-Translate` — 4 个家族
401401

402402
- [Qwen3-LiveTranslate-Flash-Realtime](groups/qwen3-livetranslate-flash-realtime.json) — Qwen3-LiveTranslate-Flash-Realtime的实时版本，一款高精度、高响应、高鲁棒性的多语言实时音视频同传大模型。依托Qwen3-Omni强大的基座能力、海量多模态数据、跨语言…
403403
- 模型：`qwen3-livetranslate-flash-realtime`
404404
- [Qwen3.5-LiveTranslate-Flash-Realtime](groups/qwen3.5-livetranslate-flash-realtime.json) — Qwen3.5-LiveTranslate-Flash的实时版本，一款高精度、高响应、高鲁棒性的多语言实时音视频同传大模型。依托Qwen3.5-Omni强大的基座能力、海量多模态数据、跨语言跨模态对齐…
405405
- 模型：`qwen3.5-livetranslate-flash-realtime`
406406
- [Qwen3.8-LiveTranslate-Flash-Realtime](groups/qwen3.8-livetranslate-flash-realtime.json) — Qwen3.8-LiveTranslate-Flash的实时版本，一款高精度、高响应、高鲁棒性的多语言实时音视频同传大模型。依托Qwen-Omni强大的基座能力、海量多模态数据、跨语言跨模态对齐和视觉…
407407
- 模型：`qwen3.8-livetranslate-flash-realtime`
408+
- [实时语音识别及翻译V1.0](groups/gummy-realtime-v1.json) — 多语言语音转写及翻译的多模态大模型。本模型提供长时间、高准确率、实时转写中/英/日/韩等10个混合语种的服务。同时支持中英日韩互译，以其他6个语种翻译成中文或英文。
409+
- 模型：`gummy-realtime-v1`
408410

409411
## 多模态嵌入 `ME` — 2 个家族
410412

0 commit comments

Comments
 (0)