From 9abccd63cf638d27693fcc6273e156a4556f3221 Mon Sep 17 00:00:00 2001
From: Soulter <905617992@qq.com>
Date: Wed, 29 Jan 2025 23:47:50 +0800
Subject: [PATCH] chore: remove stt.py

---
 stt.py | 33 ---------------------------------
 1 file changed, 33 deletions(-)
 delete mode 100644 stt.py

diff --git a/stt.py b/stt.py
deleted file mode 100644
index 9eee69b8a..000000000
--- a/stt.py
+++ /dev/null
@@ -1,33 +0,0 @@
-import torch
-from transformers import AutoModelForSpeechSeq2Seq, AutoProcessor, pipeline
-from datasets import load_dataset
-
-
-device = "cuda:0" if torch.cuda.is_available() else "cpu"
-torch_dtype = torch.float16 if torch.cuda.is_available() else torch.float32
-
-model_id = "openai/whisper-large-v3"
-
-model = AutoModelForSpeechSeq2Seq.from_pretrained(
-    model_id, torch_dtype=torch_dtype, low_cpu_mem_usage=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,
-    chunk_length_s=30,
-    batch_size=16,  # batch size for inference - set based on your device
-    torch_dtype=torch_dtype,
-    device=device,
-)
-
-dataset = load_dataset("distil-whisper/librispeech_long", "clean", split="validation")
-sample = dataset[0]["audio"]
-
-result = pipe(sample)
-print(result["text"])