well i have a faster-whisper model and two files: when i put the first one into the model it returns me nonsense subtitles, BUT then i put the second file into model it work perfect

import wave

file_path = './BAD_FILE.wav'
with wave.open(file_path, 'rb') as wf:
    channels = wf.getnchannels()
    samplerate = wf.getframerate()
    samplewidth = wf.getsampwidth()
    nframes = wf.getnframes()

    print(f"Channels: {channels}")
    print(f"Sample Rate: {samplerate}")
    print(f"Sample Width: {samplewidth} bytes")
    print(f"Number of Frames: {nframes}")
    print(f"Duration: {nframes / samplerate:.2f} seconds")
    
file_path = './GOOD_FILE.wav'
with wave.open(file_path, 'rb') as wf:
    channels = wf.getnchannels()
    samplerate = wf.getframerate()
    samplewidth = wf.getsampwidth()
    nframes = wf.getnframes()

    print(f"Channels: {channels}")
    print(f"Sample Rate: {samplerate}")
    print(f"Sample Width: {samplewidth} bytes")
    print(f"Number of Frames: {nframes}")
    print(f"Duration: {nframes / samplerate:.2f} seconds")

this code gains me output

(bad file output)
Channels: 1
Sample Rate: 48000
Sample Width: 2 bytes
Number of Frames: 480000
Duration: 10.00 seconds

(good file output)
Channels: 1
Sample Rate: 11025
Sample Width: 2 bytes
Number of Frames: 390735
Duration: 35.44 seconds

is there any other information that affects model’s results? because i dont think that sample rate has so huge effect