to run

simply install chocolatey run this on your cmd:

@"%SystemRoot%\System32\WindowsPowerShell\v1.0\powershell.exe" -NoProfile -InputFormat None -ExecutionPolicy Bypass -Command "[System.Net.ServicePointManager]::SecurityProtocol = 3072; iex ((New-Object System.Net.WebClient).DownloadString('https://community.chocolatey.org/install.ps1'))" && SET "PATH=%PATH%;%ALLUSERSPROFILE%\chocolatey\bin"

after that install ffmpeg in your device using choco install by running this on cmd after:

choco install ffmpeg

install dependencies in python IDE using:

pip install --upgrade pip

pip install --upgrade git+https://github.com/huggingface/transformers.git accelerate datasets[audio]

then lastly to inference the model:

import torch
from transformers import AutoModelForSpeechSeq2Seq, AutoProcessor, pipeline


device = "cuda:0" if torch.cuda.is_available() else "cpu"
torch_dtype = torch.float16 if torch.cuda.is_available() else torch.float32

model_id = "washeed/audio-transcribe"

model = AutoModelForSpeechSeq2Seq.from_pretrained(
    model_id, torch_dtype=torch_dtype, low_cpu_mem_usage=True, use_safetensors=True
)
model.to(device)

processor = AutoProcessor.from_pretrained(model_id)

pipe = pipeline(
    "automatic-speech-recognition",
    model=model,
    tokenizer=processor.tokenizer,
    feature_extractor=processor.feature_extractor,
    max_new_tokens=128,
    chunk_length_s=30,
    batch_size=16,
    return_timestamps=True,
    torch_dtype=torch_dtype,
    device=device,
)

result = pipe("audio.mp3")
print(result["text"])

if you want to transcribe instead of translating just replace the :

result = pipe("audio.mp3")

with

result = pipe("inference.mp3", generate_kwargs={"task": "transcribe"})