From 585a4d3e5ff8b77ee89c2ec2a9ff1e7cacd79319 Mon Sep 17 00:00:00 2001
From: 雾聪 <wucong.lyb@alibaba-inc.com>
Date: 星期二, 05 三月 2024 18:37:58 +0800
Subject: [PATCH] update docs
---
funasr/auto/auto_model.py | 40 ++++++++++++++++++++++++----------------
1 files changed, 24 insertions(+), 16 deletions(-)
diff --git a/funasr/auto/auto_model.py b/funasr/auto/auto_model.py
index a6be691..9ae9f18 100644
--- a/funasr/auto/auto_model.py
+++ b/funasr/auto/auto_model.py
@@ -28,7 +28,7 @@
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):
"""
@@ -46,6 +46,7 @@
chars = string.ascii_letters + string.digits
if isinstance(data_in, str) and data_in.startswith('http'): # url
data_in = download_from_url(data_in)
+
if isinstance(data_in, str) and os.path.exists(data_in): # wav_path; filelist: wav.scp, file.jsonl;text.txt;
_, file_extension = os.path.splitext(data_in)
file_extension = file_extension.lower()
@@ -142,11 +143,11 @@
def build_model(self, **kwargs):
assert "model" in kwargs
if "model_conf" not in kwargs:
- logging.info("download models from model hub: {}".format(kwargs.get("model_hub", "ms")))
+ logging.info("download models from model hub: {}".format(kwargs.get("hub", "ms")))
kwargs = download_model(**kwargs)
set_all_random_seed(kwargs.get("seed", 0))
-
+
device = kwargs.get("device", "cuda")
if not torch.cuda.is_available() or kwargs.get("ngpu", 1) == 0:
device = "cpu"
@@ -165,22 +166,21 @@
kwargs["token_list"] = tokenizer.token_list if hasattr(tokenizer, "token_list") else None
kwargs["token_list"] = tokenizer.get_vocab() if hasattr(tokenizer, "get_vocab") else kwargs["token_list"]
- vocab_size = len(kwargs["token_list"])
+ vocab_size = len(kwargs["token_list"]) if kwargs["token_list"] is not None else -1
else:
vocab_size = -1
-
# build frontend
frontend = kwargs.get("frontend", None)
+ kwargs["input_size"] = None
if frontend is not None:
frontend_class = tables.frontend_classes.get(frontend)
frontend = frontend_class(**kwargs["frontend_conf"])
kwargs["frontend"] = frontend
- kwargs["input_size"] = frontend.output_size()
+ kwargs["input_size"] = frontend.output_size() if hasattr(frontend, "output_size") else None
# build model
model_class = tables.model_classes.get(kwargs["model"])
- model = model_class(**kwargs, **kwargs["model_conf"], vocab_size=vocab_size)
-
+ model = model_class(**kwargs, **kwargs.get("model_conf", {}), vocab_size=vocab_size)
model.to(device)
# init_param
@@ -223,9 +223,9 @@
batch_size = kwargs.get("batch_size", 1)
# if kwargs.get("device", "cpu") == "cpu":
# 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)
@@ -238,13 +238,17 @@
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():
- results, meta_data = model.inference(**batch, **kwargs)
+ res = model.inference(**batch, **kwargs)
+ if isinstance(res, (list, tuple)):
+ results = res[0]
+ meta_data = res[1] if len(res) > 1 else {}
time2 = time.perf_counter()
asr_result_list.extend(results)
@@ -392,7 +396,8 @@
# step.3 compute punc model
if self.punc_model is not None:
if not len(result["text"]):
- result['raw_text'] = ''
+ if return_raw_text:
+ result['raw_text'] = ''
else:
self.punc_kwargs.update(cfg)
punc_res = self.inference(result["text"], model=self.punc_model, kwargs=self.punc_kwargs, **cfg)
@@ -434,10 +439,13 @@
distribute_spk(sentence_list, sv_output)
result['sentence_info'] = sentence_list
elif kwargs.get("sentence_timestamp", False):
- sentence_list = timestamp_sentence(punc_res[0]['punc_array'],
- result['timestamp'],
- raw_text,
- return_raw_text=return_raw_text)
+ if not len(result['text']):
+ sentence_list = []
+ else:
+ sentence_list = timestamp_sentence(punc_res[0]['punc_array'],
+ result['timestamp'],
+ raw_text,
+ return_raw_text=return_raw_text)
result['sentence_info'] = sentence_list
if "spk_embedding" in result: del result['spk_embedding']
--
Gitblit v1.9.1