distil-large-v3.5

pip install --upgrade pip
pip install --upgrade transformers accelerate datasets[audio]

pip install flash-attn --no-build-isolation

git clone https://github.com/ggerganov/whisper.cpp.git
cd whisper.cpp
make

pip install --upgrade huggingface_hub

from huggingface_hub import hf_hub_download

hf_hub_download(repo_id='distil-whisper/distil-large-v3.5-ggml', filename='ggml-model.bin', local_dir='./models')

pip install --upgrade pip
pip install --upgrade git+https://github.com/SYSTRAN/faster-whisper datasets[audio]

pip install --upgrade pip
pip install --upgrade openai-whisper datasets[audio]

from datasets import load_dataset
from huggingface_hub import hf_hub_download
import whisper

model_path = hf_hub_download(repo_id="distil-whisper/distil-large-v3.5-openai", filename="model.bin")
model = whisper.load_model(model_path)

dataset = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
sample = dataset[0]["audio"]["path"]

result = model.transcribe(sample, language="en")
print(result["text"])

git clone https://github.com/huggingface/candle.git

cargo clean

cargo run --example whisper --release --features symphonia -- --model distil-large-v3