[QUESTION] <title>

[LeeLaugh-jason]

Question or Issue

下载模型完成后，在网页尝试转文字，报错
Error during audio transcription: [ONNXRuntimeError] : 3 : NO_SUCHFILE : Load model from D:\Nexa-SDK_internal\faster_whisper\assets\silero_encoder_v5.onnx failed:Load model D:\Nexa-SDK_internal\faster_whisper\assets\silero_encoder_v5.onnx failed. File doesn't exist

OS

Windows10

Python Version

3.12

Nexa SDK Version

No response

GPU (if using one)

No response

[Davidqian123]

which model did you try?

[yorkew-east8]

Same problem.

model: faster-whisper-base:bin-cpu-fp16
Env: macOS 15.1.1 (M4 Pro CPU)
Nexa SDK Version: 0.0.9.6
Error Message:
Error during audio transcription: [ONNXRuntimeError] : 3 : NO_SUCHFILE : Load model from /Applications/Nexa.app/Contents/Frameworks/faster_whisper/assets/silero_encoder_v5.onnx failed:Load model /Applications/Nexa.app/Contents/Frameworks/faster_whisper/assets/silero_encoder_v5.onnx failed. File doesn't exist

I check the files in the error message and nothing was found,
ls: /Applications/Nexa.app/Contents/Frameworks/faster_whisper/: No such file or directory

I checked withnexa list , model's location shows:
/Users/xxxxxx/.cache/nexa/hub/official/faster-whisper-base/bin-cpu-fp16

so, wrong directory?

[yorkew-east8]

I'm not sure if this is related to the issue, but I keep getting a 403 error whenever I try to pull the model now...

$ nexa pull omniVLM:q8_0
Downloading omniVLM/q8_0.gguf...
An error occurred while downloading or processing the model: An unexpected error occurred: 403 Client Error: Forbidden for url: https://public-storage.nexa4ai.com/omniVLM/q8_0.gguf
Failed to pull model omniVLM:q8_0. If you are using local path, be sure to add --local_path and --model_type flags.

[xsxszab]

This issue has been resolved. You should now be able to run nexa pull omniVLM:q8_0 without any problems.