Transcript Generation Stuck at Intermittent Time Marks

[OmarKhaled511]

It’s working well, but sometimes when it's generating the transcript, it gets stuck at minute 4, 7, or 10, and it won’t finish. I’ve tried all possible solutions: lowering the temperature, reducing the number of threads, splitting the long 30-minute WAV file into smaller parts (I even tried 5-minute chunks), but the same issue keeps happening

this is my log

./bin/main -f output.wav -m models/models/ggml-large-v2.bin  --ov-e-device GPU
whisper_init_from_file_with_params_no_state: loading model from 'models/models/ggml-large-v2.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_cuda_init: GGML_CUDA_FORCE_MMQ:    no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 CUDA devices:
  Device 0: NVIDIA GeForce RTX 4070 Ti, compute capability 8.9, VMM: yes
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       = 51865
whisper_model_load: n_audio_ctx   = 1500
whisper_model_load: n_audio_state = 1280
whisper_model_load: n_audio_head  = 20
whisper_model_load: n_audio_layer = 32
whisper_model_load: n_text_ctx    = 448
whisper_model_load: n_text_state  = 1280
whisper_model_load: n_text_head   = 20
whisper_model_load: n_text_layer  = 32
whisper_model_load: n_mels        = 80
whisper_model_load: ftype         = 1
whisper_model_load: qntvr         = 0
whisper_model_load: type          = 5 (large)
whisper_model_load: adding 1608 extra tokens
whisper_model_load: n_langs       = 99
whisper_default_buffer_type: using device CUDA0 (NVIDIA GeForce RTX 4070 Ti)
whisper_model_load:    CUDA0 total size =  3093.99 MB
whisper_model_load: model size    = 3093.99 MB
whisper_backend_init_gpu: using CUDA0 backend
whisper_init_state: kv self size  =   83.89 MB
whisper_init_state: kv cross size =  251.66 MB
whisper_init_state: kv pad  size  =    7.86 MB
whisper_init_state: compute buffer (conv)   =   35.65 MB
whisper_init_state: compute buffer (encode) =  212.29 MB
whisper_init_state: compute buffer (cross)  =    9.25 MB
whisper_init_state: compute buffer (decode) =  100.02 MB

system_info: n_threads = 4 / 20 | 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 'output.wav' (25758918 samples, 1609.9 sec), 4 threads, 1 processors, 5 beams + best of 5, lang = en, task = transcribe, timestamps = 1 ...