#8589 No available channel for model whisper-1 under group gemini (distributor) (request id: 202610301616382384645258268d9d64Y

2408**c8c6 Posted at: 1 hour ago

No available channel for model whisper-1 under group gemini (distributor) (request id: 202610301616382384645258268d9d64YAeJ49D):
Traceback (most recent call last):
File "videotrans\util\TestSTT.py", line 21, in run
File "videotrans\recognition\__init__.py", line 121, in run
File "videotrans\recognition\_base.py", line 99, in run
File "videotrans\recognition\_openairecognapi.py", line 39, in _exec
File "videotrans\recognition\_openairecognapi.py", line 99, in _thrid_api
File "openai\_utils\_utils.py", line 298, in wrapper
File "openai\resources\audio\transcriptions.py", line 485, in create
File "openai\_base_client.py", line 1332, in post
File "openai\_base_client.py", line 1105, in request
openai.InternalServerError: Error code: 503 - {'error': {'code': 'model_not_found', 'message': 'No available channel for model whisper-1 under group gemini (distributor) (request id: 202610301616382384645258268d9d64YAeJ49D)', 'type': 'new_api_error'}}


=
system:Windows-10-10.0.19045-SP0
version:v4.14
frozen:True
language:zh_CN
root_dir:D:/Program Files (x86)/pyvideotrans4.14

1 Replies

#1 DeepSeek reply at 1 hour ago

这是第三方中转站(one-api/new-api)返回的错误,并非软件本身故障:model_not_found 和 No available channel for model whisper-1 under group gemini 表示你为“OpenAI 语音识别 API”渠道填写的 API 地址和密钥实际属于一个聚合中转站,而该站为你的密钥指定的分组(gemini)下没有 whisper-1 这个语音识别模型可用。因此软件无法完成识别,直接返回 503。

处理办法(按顺序尝试):

  1. 登录你填写的那个中转站后台,确认你的密钥所在分组确实开通了 whisper-1(或其他语音识别模型);从 group gemini 看,你的密钥很可能是 Gemini 分组,不包含 OpenAI 语音模型,因此需要换到包含 whisper 的分组,或换一个可用模型。
  2. 如果该站确实不提供 whisper-1,就在软件中改用官方地址:菜单 → 翻译设置 → OpenAI 语音识别API,将 API 地址改为 https://api.openai.com/v1,并填入官方 OpenAI 密钥。该地址与字幕翻译里的 OpenAI 渠道是分开配置的,不要混填。
  3. 如果只是想把语音转成字幕,最省事的办法是改用内置的 faster-whisper(内置) + large-v3-turbo 模型(免费、离线、不依赖任何 API),主误区是误以为必须有在线识别 API。
  4. 另外两点建议一并修正:

    • 你的软件安装在 D:/Program Files (x86)/pyvideotrans4.14,路径含空格和括号,属于系统受保护目录,易引发权限问题以及 ffmpeg 路径解析报错。请整体移动到 D:/pyvideotrans 这类全英文、无空格的简短路径。
    • 当前版本为 v4.14,建议更新到最新版。

请查阅相关文档:

Thinking...
Post Your Reply
If you have more than 50 messages, you will no longer receive an automatic reply. Please ask a new question!
Open source and free maintenance is not easy. If this project is helpful to you, please consider making a small donation to help the project continue to maintain and update.

Dondate via ko-fi.com

Related resource