CPU hung . First time running transcibe

[arunpatil1988]

Hi Guys - This is first time i installed whisper and all the related components. I gave the below command and it is stuck

whisper /home/abcUser/file_2135900566_3093552530792048272.wav --model medium
100%|█████████████████████████████████████| 1.42G/1.42G [01:04<00:00, 23.8MiB/s]
/usr/local/lib/python3.10/site-packages/whisper/transcribe.py:114: UserWarning: FP16 is not supported on CPU; using FP32 instead
warnings.warn("FP16 is not supported on CPU; using FP32 instead")
Detecting language using up to the first 30 seconds. Use --language to specify the language
Detected language: English

It is stuck at this point and nothing happening . Is it common and below is the system details. Let me know if its good enough to run whisper.

This is the system hardware details.

Architecture: x86_64
CPU op-mode(s): 32-bit, 64-bit
Byte Order: Little Endian
CPU(s): 2
On-line CPU(s) list: 0,1
Thread(s) per core: 1
Core(s) per socket: 1
Socket(s): 2
NUMA node(s): 1
Vendor ID: GenuineIntel
CPU family: 6
Model: 85
Model name: Intel(R) Xeon(R) Gold 6154 CPU @ 3.00GHz
Stepping: 4
CPU MHz: 2992.968
BogoMIPS: 5985.93
Hypervisor vendor: VMware
Virtualization type: full
L1d cache: 32K
L1i cache: 32K
L2 cache: 1024K
L3 cache: 25344K
NUMA node0 CPU(s): 0,1

[arunpatil1988]

nvm - i killed the session and reran it again , was able to get the transcription. However on rerunning it was a lot faster, still taking on average 5 seconds. how do i speed this up.

[bangyuanzhu]

The medium model size costs more time. For English transcription, the small size is enough to get an acceptable WER.

Another way is to move the model implement on a more powerful CPU/GPU