From 28ccfbfc51068a663a80764e14074df5edf2b5ba Mon Sep 17 00:00:00 2001
From: kongdeqiang <kongdeqiang960204@163.com>
Date: 星期五, 13 三月 2026 17:41:41 +0800
Subject: [PATCH] 提交
---
runtime/python/onnxruntime/funasr_onnx/paraformer_bin.py | 29 ++++++++++++++++++++++++-----
1 files changed, 24 insertions(+), 5 deletions(-)
diff --git a/runtime/python/onnxruntime/funasr_onnx/paraformer_bin.py b/runtime/python/onnxruntime/funasr_onnx/paraformer_bin.py
index 2cd43a8..bde7f44 100644
--- a/runtime/python/onnxruntime/funasr_onnx/paraformer_bin.py
+++ b/runtime/python/onnxruntime/funasr_onnx/paraformer_bin.py
@@ -62,7 +62,7 @@
if quantize:
model_file = os.path.join(model_dir, "model_quant.onnx")
if not os.path.exists(model_file):
- print(".onnx is not exist, begin to export onnx")
+ print(".onnx does not exist, begin to export onnx")
try:
from funasr import AutoModel
except:
@@ -175,7 +175,23 @@
plt.savefig(plotname, bbox_inches="tight")
def load_data(self, wav_content: Union[str, np.ndarray, List[str]], fs: int = None) -> List:
+ def convert_to_wav(input_path, output_path):
+ from pydub import AudioSegment
+ try:
+ audio = AudioSegment.from_mp3(input_path)
+ audio.export(output_path, format="wav")
+ print("闊抽鏂囦欢涓簃p3鏍煎紡锛屽凡杞崲涓簑av鏍煎紡")
+
+ except Exception as e:
+ print(f"杞崲澶辫触:{e}")
+
def load_wav(path: str) -> np.ndarray:
+ if not path.lower().endswith('.wav'):
+ import os
+ input_path = path
+ path = os.path.splitext(path)[0]+'.wav'
+ convert_to_wav(input_path,path) #灏唌p3鏍煎紡杞崲鎴恮av鏍煎紡
+
waveform, _ = librosa.load(path, sr=fs)
return waveform
@@ -285,7 +301,7 @@
model_eb_file = os.path.join(model_dir, "model_eb.onnx")
if not (os.path.exists(model_eb_file) and os.path.exists(model_bb_file)):
- print(".onnx is not exist, begin to export onnx")
+ print(".onnx does not exist, begin to export onnx")
try:
from funasr import AutoModel
except:
@@ -322,6 +338,10 @@
self.pred_bias = config["model_conf"]["predictor_bias"]
else:
self.pred_bias = 0
+ if "lang" in config:
+ self.language = config["lang"]
+ else:
+ self.language = None
def __call__(
self, wav_content: Union[str, np.ndarray, List[str]], hotwords: str, **kwargs
@@ -331,7 +351,6 @@
# ) -> List:
# make hotword list
hotwords, hotwords_length = self.proc_hotword(hotwords)
- # import pdb; pdb.set_trace()
[bias_embed] = self.eb_infer(hotwords, hotwords_length)
# index from bias_embed
bias_embed = bias_embed.transpose(1, 0, 2)
@@ -411,10 +430,10 @@
return np.array(hotwords)
hotword_int = [word_map(i) for i in hotwords]
- # import pdb; pdb.set_trace()
+
hotword_int.append(np.array([1]))
hotwords = pad_list(hotword_int, pad_value=0, max_len=10)
- # import pdb; pdb.set_trace()
+
return hotwords, hotwords_length
def bb_infer(
--
Gitblit v1.9.1