From c4fa4c5efd4965b4514194179cfed6e1faa76c42 Mon Sep 17 00:00:00 2001
From: 语帆 <yf352572@alibaba-inc.com>
Date: 星期四, 22 二月 2024 16:10:12 +0800
Subject: [PATCH] test
---
funasr/auto/auto_model.py | 12 +++++++++---
1 files changed, 9 insertions(+), 3 deletions(-)
diff --git a/funasr/auto/auto_model.py b/funasr/auto/auto_model.py
index e5faa2a..9db8c01 100644
--- a/funasr/auto/auto_model.py
+++ b/funasr/auto/auto_model.py
@@ -23,7 +23,7 @@
from funasr.models.campplus.cluster_backend import ClusterBackend
except:
print("If you want to use the speaker diarization, please `pip install hdbscan`")
-
+import pdb
def prepare_data_iterator(data_in, input_len=None, data_type=None, key=None):
"""
@@ -153,15 +153,18 @@
# build tokenizer
tokenizer = kwargs.get("tokenizer", None)
+ pdb.set_trace()
if tokenizer is not None:
tokenizer_class = tables.tokenizer_classes.get(tokenizer)
+ pdb.set_trace()
tokenizer = tokenizer_class(**kwargs["tokenizer_conf"])
+ pdb.set_trace()
kwargs["tokenizer"] = tokenizer
kwargs["token_list"] = tokenizer.token_list
vocab_size = len(tokenizer.token_list)
else:
vocab_size = -1
-
+ pdb.set_trace()
# build frontend
frontend = kwargs.get("frontend", None)
if frontend is not None:
@@ -215,7 +218,7 @@
# batch_size = 1
key_list, data_list = prepare_data_iterator(input, input_len=input_len, data_type=kwargs.get("data_type", None), key=key)
-
+
speed_stats = {}
asr_result_list = []
num_samples = len(data_list)
@@ -228,15 +231,18 @@
data_batch = data_list[beg_idx:end_idx]
key_batch = key_list[beg_idx:end_idx]
batch = {"data_in": data_batch, "key": key_batch}
+
if (end_idx - beg_idx) == 1 and kwargs.get("data_type", None) == "fbank": # fbank
batch["data_in"] = data_batch[0]
batch["data_lengths"] = input_len
time1 = time.perf_counter()
with torch.no_grad():
+ pdb.set_trace()
results, meta_data = model.inference(**batch, **kwargs)
time2 = time.perf_counter()
+ pdb.set_trace()
asr_result_list.extend(results)
# batch_data_time = time_per_frame_s * data_batch_i["speech_lengths"].sum().item()
--
Gitblit v1.9.1