mirror of
https://git.openapi.site/https://github.com/desirecore/config-center.git
synced 2026-06-06 05:50:50 +08:00
Batch update from official docs audit - price corrections, context window fixes, field report updates across all providers. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2.3 KiB
2.3 KiB
详细字段取值表 - compute/providers/local-whisper.json
- provider:
local-whisper - priceCurrency:
USD - generatedAt:
2026-04-23T15:11:31.654Z
来源
- https://huggingface.co/openai/whisper-large-v3
- https://github.com/openai/whisper
- https://zenmux.ai/models
- https://zenmux.ai/api/v1/models
whisper-large-v3
- ZenMux匹配级别:
none - ZenMux候选: (none)
| 字段 | 当前值 | 建议值 | 结论 | 依据/说明 |
|---|---|---|---|---|
modelName |
"whisper-large-v3" |
"whisper-large-v3" |
待确认 | ZenMux无稳定匹配 |
displayName |
"Whisper Large V3" |
"Whisper Large V3" |
保持 | 展示字段,需按产品命名策略 |
serviceType |
["asr"] |
["asr"] |
保持 | 服务路由字段,优先本项目约定 |
contextWindow |
0 |
0 |
保持 | 已查 https://huggingface.co/openai/whisper-large-v3 与 https://github.com/openai/whisper ,whisper-large-v3 为语音转文本模型,官方未定义与聊天模型同口径的 context window,当前以 0 记录为不适用 |
maxOutputTokens |
0 |
0 |
保持 | 已查 https://huggingface.co/openai/whisper-large-v3 与 https://github.com/openai/whisper ,官方未提供 transcription 模型的 max output tokens 规格,当前以 0 记录为不适用 |
inputPrice |
(缺省) | (缺省) | 待确认 | ZenMux无稳定价格可用,需官方价格页复核 |
outputPrice |
(缺省) | (缺省) | 待确认 | ZenMux无稳定价格可用,需官方价格页复核 |
capabilities |
["asr","multilingual"] |
["asr","multilingual"] |
保持 | ZenMux无明确能力映射差异 |
defaultTemperature |
null |
null |
保持 | 已复核 Whisper 官方仓库与 whisper-large-v3 模型卡;Whisper 是 ASR/翻译模型,官方公开的是转录解码策略而非本地 OpenAI 兼容服务的固定模型级默认采样值,当前保持 null |
defaultTopP |
null |
null |
保持 | 已复核 Whisper 官方仓库与模型卡,未提供 ASR 模型的 top_p 采样默认值,当前保持 null |
extra |
{"maxAudioLength":7200,"supportedInputFormats":["wav","mp3","flac","ogg","webm"],"streamingSupported":true} |
{"maxAudioLength":7200,"supportedInputFormats":["wav","mp3","flac","ogg","webm"],"streamingSupported":true} |
待确认 | 扩展字段为本地schema,需业务侧定义 |