Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

No transcription, only "!!!!!!!" - Solved #2618

Open
andy144 opened this issue Dec 9, 2024 · 2 comments
Open

No transcription, only "!!!!!!!" - Solved #2618

andy144 opened this issue Dec 9, 2024 · 2 comments

Comments

@andy144
Copy link

andy144 commented Dec 9, 2024

I installed it with Vulkan on Archlinux.
When launched it for jfk.wav file I get this:

$ ./build/bin/main -m models/ggml-medium.en.bin -f samples/jfk.wav
whisper_init_from_file_with_params_no_state: loading model from 'models/ggml-medium.en.bin'
whisper_init_with_params_no_state: use gpu = 1
whisper_init_with_params_no_state: flash attn = 0
whisper_init_with_params_no_state: gpu_device = 0
whisper_init_with_params_no_state: dtw = 0
ggml_vulkan: Found 1 Vulkan devices:
ggml_vulkan: 0 = AMD Radeon RX 6750 XT (AMD open-source driver) | uma: 0 | fp16: 1 | warp size: 64
whisper_init_with_params_no_state: devices = 2
whisper_init_with_params_no_state: backends = 2
whisper_model_load: loading model
whisper_model_load: n_vocab = 51864
whisper_model_load: n_audio_ctx = 1500
whisper_model_load: n_audio_state = 1024
whisper_model_load: n_audio_head = 16
whisper_model_load: n_audio_layer = 24
whisper_model_load: n_text_ctx = 448
whisper_model_load: n_text_state = 1024
whisper_model_load: n_text_head = 16
whisper_model_load: n_text_layer = 24
whisper_model_load: n_mels = 80
whisper_model_load: ftype = 1
whisper_model_load: qntvr = 0
whisper_model_load: type = 4 (medium)
whisper_model_load: adding 1607 extra tokens
whisper_model_load: n_langs = 99
whisper_default_buffer_type: using device Vulkan0 (AMD Radeon RX 6750 XT)
ggml_vulkan: Compiling shaders..............................Done!
whisper_model_load: Vulkan0 total size = 1533.14 MB
whisper_model_load: model size = 1533.14 MB
whisper_backend_init_gpu: using Vulkan0 backend
whisper_init_state: kv self size = 50.33 MB
whisper_init_state: kv cross size = 150.99 MB
whisper_init_state: kv pad size = 6.29 MB
whisper_init_state: compute buffer (conv) = 29.51 MB
whisper_init_state: compute buffer (encode) = 170.15 MB
whisper_init_state: compute buffer (cross) = 7.72 MB
whisper_init_state: compute buffer (decode) = 99.10 MB

system_info: n_threads = 4 / 16 | AVX = 1 | AVX2 = 1 | AVX512 = 0 | FMA = 1 | NEON = 0 | ARM_FMA = 0 | F16C = 1 | FP16_VA = 0 | WASM_SIMD = 0 | SSE3 = 1 | SSSE3 = 1 | VSX = 0 | COREML = 0 | OPENVINO = 0 |

main: processing 'samples/jfk.wav' (176000 samples, 11.0 sec), 4 threads, 1 processors, 5 beams + best of 5, lang = en, task = transcribe, timestamps = 1 ...

[00:00:00.000 --> 00:00:30.000] !!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!

whisper_print_timings: load time = 478.96 ms
whisper_print_timings: fallbacks = 5 p / 0 h
whisper_print_timings: mel time = 8.63 ms
whisper_print_timings: sample time = 1730.73 ms / 6600 runs ( 0.26 ms per run)
whisper_print_timings: encode time = 770.19 ms / 1 runs ( 770.19 ms per run)
whisper_print_timings: decode time = 57.50 ms / 6 runs ( 9.58 ms per run)
whisper_print_timings: batchd time = 63483.95 ms / 6570 runs ( 9.66 ms per run)
whisper_print_timings: prompt time = 0.00 ms / 1 runs ( 0.00 ms per run)
whisper_print_timings: total time = 66696.83 ms

@gn64
Copy link
Contributor

gn64 commented Dec 10, 2024

I think this bug is related to #2596

@andy144
Copy link
Author

andy144 commented Dec 15, 2024

Solved it by uninstalling amdvlk and lib32-amdvlk drivers.
It works fine with vulkan-radeon and lib32-vulkan-radeon drivers only.

@andy144 andy144 changed the title No transcription, only "!!!!!!!" No transcription, only "!!!!!!!" - Solved Dec 15, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants