vibe: Bug: Crash on loading model

What happened?

After I hit “Transcribe”, the app crashes.

Since, at least from what I’ve noticed, there are no crash logs, here’s what the cmd log shows:

log
C:\Windows\System32>[2024-05-22T01:57:23Z DEBUG vibe_desktop] Vibe App Running
[2024-05-22T01:57:24Z DEBUG vibe_desktop::setup] webview version: 125.0.2535.51
[2024-05-22T01:57:33Z DEBUG vibe::model] Transcribe called with {
      "path": "D:\\2023-11-30 11-25-58.mkv",
      "model_path": "C:\\Users\\AutumnLeaf\\AppData\\Local\\github.com.thewh1teagle.vibe\\ggml-medium.bin",
      "lang": "en",
      "verbose": false,
      "n_threads": 4,
      "init_prompt": "",
      "temperature": 0.4
    }
[2024-05-22T01:57:33Z DEBUG vibe::audio] input is D:\2023-11-30 11-25-58.mkv and output is C:\Users\AUTUMN~1\AppData\Local\Temp\.tmptp0lsV.wav
[2024-05-22T01:57:33Z DEBUG vibe::audio::encoder] decoder channel layout is 2
[2024-05-22T01:57:33Z DEBUG vibe::audio::encoder] +-----------+
    |    in     |default--[48000Hz fltp:stereo]--auto_aresample_0:default
    | (abuffer) |
    +-----------+

                                                       +---------------+
    Parsed_anull_0:default--[16000Hz s16:mono]--default|      out      |
                                                       | (abuffersink) |
                                                       +---------------+

                                                         +----------------+
    auto_aresample_0:default--[16000Hz s16:mono]--default| Parsed_anull_0 |default--[16000Hz s16:mono]--out:default
                                                         |    (anull)     |
                                                         +----------------+

                                              +------------------+
    in:default--[48000Hz fltp:stereo]--default| auto_aresample_0 |default--[16000Hz s16:mono]--Parsed_anull_0:default
                                              |   (aresample)    |
                                              +------------------+


[2024-05-22T01:57:33Z DEBUG vibe::audio] wav reader read from "C:\\Users\\AUTUMN~1\\AppData\\Local\\Temp\\.tmptp0lsV.wav"
[2024-05-22T01:57:33Z DEBUG vibe::audio] parsing C:\Users\AUTUMN~1\AppData\Local\Temp\.tmptp0lsV.wav
[2024-05-22T01:57:33Z DEBUG vibe::model] open model...

Steps to reproduce

  1. Open Vibe
  2. Attempt to Transcribe
  3. Crash when trying to load model

Tried on Windows 10 first, and now on Windows 11. Also, my brother’s pc (Windows 10) for some reason has no issue with Vibe.

Could it be because I’ve got an old cpu (i7-3770 vs my brother’s Ryzen 5 2600) or motherboard or something like that that there’s some conflict happening? In case it helps, I am able to run Stable Diffusion locally without issues (both Automatic 1111 and ComfyUI).

I should also note that the user shown on the logs of Vibe is AUTUMN~1 instead of AutumnLeaf. Since I’ve seen a few past issues here due to hebraic user names, perhaps the tilde (which shouldn’t even be there) could be a cause.

What OS are you seeing the problem on?

Window

logs

Relevant log output

App Version: 1.0.7
Commit Hash: 99ae746dc02135ad7a27ec0f9adafe016b8c96e4
Arch: x86_64
Platform: windows
Kernel Version: 10.0.22631
OS: windows
OS Version: 10.0.22631
Models: ggml-medium.bin
Default Model: "C:\\Users\\AutumnLeaf\\AppData\\Local\\github.com.thewh1teagle.vibe\\ggml-medium.bin"

About this issue

  • Original URL
  • State: closed
  • Created 2 years ago
  • Comments: 31 (18 by maintainers)

Most upvoted comments

Yup. These results might be a good form of advertisement to increase interest in your project.

And, in my opinion, the best part is that it is also run locally.

Thank you once again for you efforts!

That’s amazing! It’s nearly as fast as high-quality transcriptions from paid APIs. Now, anyone with Nvidia GPUs can easily turn their PC into a high-quality transcription machine 😃

Amazing! Thanks for your patience 😃

Thank you!

speed that you get when transcribing

On the sample you mentioned above (11 seconds of sound), it took 19 seconds.

It works now! Here’s the log just in case:

logs
C:\Users\AutumnLeaf>set RUST_LOG=vibe=debug,whisper_rs=debug

C:\Users\AutumnLeaf>%localappdata%\vibe\vibe.exe

C:\Users\AutumnLeaf>[2024-05-23T00:30:25Z DEBUG vibe_desktop] Vibe App Running
[2024-05-23T00:30:25Z DEBUG vibe_desktop::setup] webview version: 125.0.2535.51
[2024-05-23T00:30:25Z DEBUG vibe_desktop::setup] CPU Features:
    AVX: true
    AVX2: false
    AVX512: false
    AVX512-VBMI: false
    AVX512-VNNI: false
    FMA: false
    F16C: true
[2024-05-23T00:30:25Z DEBUG vibe_desktop::setup] COMMIT_HASH: cc1bb4f721a794c58081b139e57808c6ec8e00a5
[2024-05-23T00:30:30Z DEBUG vibe::model] Transcribe called with {
      "path": "C:\\Users\\AutumnLeaf\\Downloads\\whisper-bin-x64\\samples_single.wav",
      "model_path": "C:\\Users\\AutumnLeaf\\AppData\\Local\\github.com.thewh1teagle.vibe\\ggml-medium.bin",
      "lang": "en",
      "verbose": false,
      "n_threads": 4,
      "init_prompt": "",
      "temperature": 0.4
    }
[2024-05-23T00:30:30Z DEBUG vibe::audio] input is C:\Users\AutumnLeaf\Downloads\whisper-bin-x64\samples_single.wav and output is C:\Users\AUTUMN~1\AppData\Local\Temp\.tmpHz2Pyh.wav
[2024-05-23T00:30:30Z DEBUG vibe::audio::encoder] decoder channel layout is 0
[2024-05-23T00:30:30Z DEBUG vibe::audio::encoder] +-----------+
    |    in     |default--[16000Hz s16:mono]--Parsed_anull_0:default
    | (abuffer) |
    +-----------+

                                                       +---------------+
    Parsed_anull_0:default--[16000Hz s16:mono]--default|      out      |
                                                       | (abuffersink) |
                                                       +---------------+

                                           +----------------+
    in:default--[16000Hz s16:mono]--default| Parsed_anull_0 |default--[16000Hz s16:mono]--out:default
                                           |    (anull)     |
                                           +----------------+


[2024-05-23T00:30:30Z DEBUG vibe::audio] wav reader read from "C:\\Users\\AUTUMN~1\\AppData\\Local\\Temp\\.tmpHz2Pyh.wav"
[2024-05-23T00:30:31Z DEBUG vibe::audio] parsing C:\Users\AUTUMN~1\AppData\Local\Temp\.tmpHz2Pyh.wav
[2024-05-23T00:30:31Z DEBUG vibe::model] open model...
[2024-05-23T00:30:31Z INFO  whisper_rs::whisper_sys_log] whisper_init_from_file_with_params_no_state: loading model from 'C:\Users\AutumnLeaf\AppData\Local\github.com.thewh1teagle.vibe\ggml-medium.bin'
[2024-05-23T00:30:31Z INFO  whisper_rs::whisper_sys_log] whisper_model_load: loading model
[2024-05-23T00:30:31Z INFO  whisper_rs::whisper_sys_log] whisper_model_load: n_vocab       = 51865
[2024-05-23T00:30:31Z INFO  whisper_rs::whisper_sys_log] whisper_model_load: n_audio_ctx   = 1500
[2024-05-23T00:30:31Z INFO  whisper_rs::whisper_sys_log] whisper_model_load: n_audio_state = 1024
[2024-05-23T00:30:31Z INFO  whisper_rs::whisper_sys_log] whisper_model_load: n_audio_head  = 16
[2024-05-23T00:30:31Z INFO  whisper_rs::whisper_sys_log] whisper_model_load: n_audio_layer = 24
[2024-05-23T00:30:31Z INFO  whisper_rs::whisper_sys_log] whisper_model_load: n_text_ctx    = 448
[2024-05-23T00:30:31Z INFO  whisper_rs::whisper_sys_log] whisper_model_load: n_text_state  = 1024
[2024-05-23T00:30:31Z INFO  whisper_rs::whisper_sys_log] whisper_model_load: n_text_head   = 16
[2024-05-23T00:30:31Z INFO  whisper_rs::whisper_sys_log] whisper_model_load: n_text_layer  = 24
[2024-05-23T00:30:31Z INFO  whisper_rs::whisper_sys_log] whisper_model_load: n_mels        = 80
[2024-05-23T00:30:31Z INFO  whisper_rs::whisper_sys_log] whisper_model_load: ftype         = 1
[2024-05-23T00:30:31Z INFO  whisper_rs::whisper_sys_log] whisper_model_load: qntvr         = 0
[2024-05-23T00:30:31Z INFO  whisper_rs::whisper_sys_log] whisper_model_load: type          = 4 (medium)
[2024-05-23T00:30:31Z INFO  whisper_rs::whisper_sys_log] whisper_model_load: adding 1608 extra tokens
[2024-05-23T00:30:31Z INFO  whisper_rs::whisper_sys_log] whisper_model_load: n_langs       = 99
[2024-05-23T00:30:35Z INFO  whisper_rs::whisper_sys_log] whisper_model_load:      CPU total size =  1533.14 MB
[2024-05-23T00:30:37Z INFO  whisper_rs::whisper_sys_log] whisper_model_load: model size    = 1533.14 MB
[2024-05-23T00:30:37Z INFO  whisper_rs::whisper_sys_log] whisper_init_state: kv self size  =  132.12 MB
[2024-05-23T00:30:37Z INFO  whisper_rs::whisper_sys_log] whisper_init_state: kv cross size =  147.46 MB
[2024-05-23T00:30:37Z INFO  whisper_rs::whisper_sys_log] whisper_init_state: compute buffer (conv)   =   28.68 MB
[2024-05-23T00:30:37Z INFO  whisper_rs::whisper_sys_log] whisper_init_state: compute buffer (encode) =  594.22 MB
[2024-05-23T00:30:37Z INFO  whisper_rs::whisper_sys_log] whisper_init_state: compute buffer (cross)  =    7.85 MB
[2024-05-23T00:30:37Z INFO  whisper_rs::whisper_sys_log] whisper_init_state: compute buffer (decode) =  138.87 MB
[2024-05-23T00:30:37Z DEBUG vibe::model] set language to Some("en")
[2024-05-23T00:30:37Z DEBUG vibe::model] setting temperature to 0.4
[2024-05-23T00:30:37Z DEBUG vibe::model] setting init prompt to
[2024-05-23T00:30:37Z DEBUG vibe::model] setting n threads to 4
[2024-05-23T00:30:37Z DEBUG vibe::model] set start time...
[2024-05-23T00:30:37Z DEBUG vibe::model] setting state full...
[2024-05-23T00:30:37Z DEBUG vibe::model] progress callback 0
[2024-05-23T00:30:37Z DEBUG vibe_desktop::cmd] set_progress_bar 0
[2024-05-23T00:30:56Z DEBUG vibe::model] progress callback 100
[2024-05-23T00:30:56Z DEBUG vibe_desktop::cmd] set_progress_bar 100
[2024-05-23T00:30:56Z DEBUG vibe::model] getting segments count...
[2024-05-23T00:30:56Z DEBUG vibe::model] found 1 segments
[2024-05-23T00:30:56Z DEBUG vibe::model] looping segments...

Should I close the issue or is there anything else you’d like me to test?