Example how to use with whisper.cpp
git clone https://github.com/ggerganov/whisper.cpp.git
cd whisper.cpp
git reset --hard 0b9af32a8b3fa7e2ae5f15a9a08f5b10394993f5
make
one of the following:
./main -m ggml-model-fi-tiny.bin -f INSERT_YOUR_FILENAME_HERE.wav -l fi
./main -m ggml-model-fi-medium.bin -f INSERT_YOUR_FILENAME_HERE.wav -l fi
./main -m ggml-model-fi-large.bin -f INSERT_YOUR_FILENAME_HERE.wav -l fi
./main -m ggml-model-fi-large-v3.bin -f INSERT_YOUR_FILENAME_HERE.wav -l fi
Sample output should look something like this:
(finetuneEnv) rasmus@DESKTOP-59O9VN1:/mnt/f/Omat_opiskelut/whisper_transformaatio/whisper.cpp$ ./main -m ggml-model-fi-medium.bin -f oma_nauhoitus_16khz.wav -l fi
whisper_init_from_file_with_params_no_state: loading model from 'ggml-model-fi-medium.bin'
whisper_model_load: loading model
whisper_model_load: n_vocab = 51865
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 1608 extra tokens
whisper_model_load: n_langs = 99
whisper_model_load: CPU buffer size = 1533.52 MB
whisper_model_load: model size = 1533.14 MB
whisper_init_state: kv self size = 132.12 MB
whisper_init_state: kv cross size = 147.46 MB
whisper_init_state: compute buffer (conv) = 25.61 MB
whisper_init_state: compute buffer (encode) = 170.28 MB
whisper_init_state: compute buffer (cross) = 7.85 MB
whisper_init_state: compute buffer (decode) = 98.32 MB
system_info: n_threads = 4 / 8 | AVX = 1 | AVX2 = 1 | AVX512 = 0 | FMA = 1 | NEON = 0 | ARM_FMA = 0 | METAL = 0 | F16C = 1 | FP16_VA = 0 | WASM_SIMD = 0 | BLAS = 0 | SSE3 = 1 | SSSE3 = 1 | VSX = 0 | CUDA = 0 | COREML = 0 | OPENVINO = 0 |
main: processing 'oma_nauhoitus_16khz.wav' (144160 samples, 9.0 sec), 4 threads, 1 processors, 5 beams + best of 5, lang = fi, task = transcribe, timestamps = 1 ...
[00:00:00.000 --> 00:00:09.000] Moi, nimeni on Rasmus ja testaan tekoälymallia, joka tunnistaa puheeni ja kirjoittaa sen tekstiksi.