| # 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"})``` | |