What happened?
Cannot use faster-whisper models.
Steps to reproduce
Download a faster whisper model from huggingface.co/Systran, rename it to ggml-faster-small-en.bin select it in the app settings and click transcribe.
What OS are you seeing the problem on?
Window
Relevant log output
failed to open model
Caused by:
Failed to create a new whisper context.
Location:
core\src\transcribe.rs:38:65
App Version: vibe 3.0.5
Commit Hash: 46c5dd1
Arch: x86_64
Platform: windows
Kernel Version: 10.0.26100
OS: windows
OS Version: 10.0.26100
Cuda Version: n/a
Models: faster-distil-whisper-small.en.bin, ggml-base-en.bin, ggml-faster-small-en.bin, ggml-small-en.bin, ggml-small.bin
Default Model: "D:\\Potable Apps\\WinWhisper-win-Portable\\current\\Models\\ggml-faster-small-en.bin"
Cargo features: vulkan
{"avx":{"enabled":true,"support":true},"avx2":{"enabled":true,"support":true},"f16c":{"enabled":true,"support":true},"fma":{"enabled":true,"support":true}}
<details>
<summary>logs</summary>
whisper_full_with_state: failed to decode
cmd: "C:\\ProgramData\\chocolatey\\bin\\ffmpeg.exe" "-i" "D:\\redacted folder name\\redacted folder name\\redacted video name.mkv" "-ar" "16000" "-ac" "1" "-c:a" "pcm_s16le" "C:\\Users\\redacted user name\\AppData\\Local\\Temp\\vibe_temp_2025-06-30\\fc0bdbfe7c71b518.wav" "-hide_banner" "-y" "-loglevel" "error"
whisper_model_load: invalid model data (bad magic)
whisper_init_with_params_no_state: failed to load model
whisper_model_load: invalid model data (bad magic)
whisper_init_with_params_no_state: failed to load model
whisper_model_load: invalid model data (bad magic)
whisper_init_with_params_no_state: failed to load model
whisper_model_load: invalid model data (bad magic)
whisper_init_with_params_no_state: failed to load model
</details>
What happened?
Cannot use faster-whisper models.
Steps to reproduce
Download a faster whisper model from huggingface.co/Systran, rename it to
ggml-faster-small-en.binselect it in the app settings and click transcribe.What OS are you seeing the problem on?
Window
Relevant log output
failed to open model Caused by: Failed to create a new whisper context. Location: core\src\transcribe.rs:38:65 App Version: vibe 3.0.5 Commit Hash: 46c5dd1 Arch: x86_64 Platform: windows Kernel Version: 10.0.26100 OS: windows OS Version: 10.0.26100 Cuda Version: n/a Models: faster-distil-whisper-small.en.bin, ggml-base-en.bin, ggml-faster-small-en.bin, ggml-small-en.bin, ggml-small.bin Default Model: "D:\\Potable Apps\\WinWhisper-win-Portable\\current\\Models\\ggml-faster-small-en.bin" Cargo features: vulkan {"avx":{"enabled":true,"support":true},"avx2":{"enabled":true,"support":true},"f16c":{"enabled":true,"support":true},"fma":{"enabled":true,"support":true}} <details> <summary>logs</summary> whisper_full_with_state: failed to decode cmd: "C:\\ProgramData\\chocolatey\\bin\\ffmpeg.exe" "-i" "D:\\redacted folder name\\redacted folder name\\redacted video name.mkv" "-ar" "16000" "-ac" "1" "-c:a" "pcm_s16le" "C:\\Users\\redacted user name\\AppData\\Local\\Temp\\vibe_temp_2025-06-30\\fc0bdbfe7c71b518.wav" "-hide_banner" "-y" "-loglevel" "error" whisper_model_load: invalid model data (bad magic) whisper_init_with_params_no_state: failed to load model whisper_model_load: invalid model data (bad magic) whisper_init_with_params_no_state: failed to load model whisper_model_load: invalid model data (bad magic) whisper_init_with_params_no_state: failed to load model whisper_model_load: invalid model data (bad magic) whisper_init_with_params_no_state: failed to load model </details>