From 806a03609df033d61f824f1ab8527eb88fe837ad Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期三, 13 十二月 2023 19:43:13 +0800
Subject: [PATCH] funasr2 paraformer biciparaformer contextuaparaformer
---
funasr/bin/asr_inference_launch.py | 65 ++++++++++++--------------------
1 files changed, 25 insertions(+), 40 deletions(-)
diff --git a/funasr/bin/asr_inference_launch.py b/funasr/bin/asr_inference_launch.py
index f61c085..6151d28 100644
--- a/funasr/bin/asr_inference_launch.py
+++ b/funasr/bin/asr_inference_launch.py
@@ -48,13 +48,13 @@
from funasr.utils.types import str2triple_str
from funasr.utils.types import str_or_none
from funasr.utils.vad_utils import slice_padding_fbank
-from funasr.utils.speaker_utils import (check_audio_list,
- sv_preprocess,
- sv_chunk,
- CAMPPlus,
- extract_feature,
+from funasr.utils.speaker_utils import (check_audio_list,
+ sv_preprocess,
+ sv_chunk,
+ extract_feature,
postprocess,
distribute_spk)
+import funasr.modules.cnn as sv_module
from funasr.build_utils.build_model_from_file import build_model_from_file
from funasr.utils.cluster_backend import ClusterBackend
from funasr.utils.modelscope_utils import get_cache_dir
@@ -818,7 +818,15 @@
format="%(asctime)s (%(module)s:%(lineno)d) %(levelname)s: %(message)s",
)
- sv_model_file = asr_model_file.replace("model.pb", "campplus_cn_common.bin")
+ sv_model_config_path = asr_model_file.replace("model.pb", "sv_model_config.yaml")
+ if not os.path.exists(sv_model_config_path):
+ sv_model_config = {'sv_model_class': 'CAMPPlus','sv_model_file': 'campplus_cn_common.bin', 'models_config': {}}
+ else:
+ with open(sv_model_config_path, 'r') as f:
+ sv_model_config = yaml.load(f, Loader=yaml.FullLoader)
+ if sv_model_config['models_config'] is None:
+ sv_model_config['models_config'] = {}
+ sv_model_file = asr_model_file.replace("model.pb", sv_model_config['sv_model_file'])
if param_dict is not None:
hotword_list_or_file = param_dict.get('hotword')
@@ -944,9 +952,15 @@
##### speaker_verification #####
##################################
# load sv model
- sv_model_dict = torch.load(sv_model_file, map_location=torch.device('cpu'))
- sv_model = CAMPPlus()
+ if ngpu > 0:
+ sv_model_dict = torch.load(sv_model_file)
+ sv_model = getattr(sv_module, sv_model_config['sv_model_class'])(**sv_model_config['models_config'])
+ sv_model.cuda()
+ else:
+ sv_model_dict = torch.load(sv_model_file, map_location=torch.device('cpu'))
+ sv_model = getattr(sv_module, sv_model_config['sv_model_class'])(**sv_model_config['models_config'])
sv_model.load_state_dict(sv_model_dict)
+ print(f'load sv model params: {sv_model_file}')
sv_model.eval()
cb_model = ClusterBackend()
vad_segments = []
@@ -969,9 +983,11 @@
embs = []
for x in wavs:
x = extract_feature([x])
+ if ngpu > 0:
+ x = x.cuda()
embs.append(sv_model(x))
embs = torch.cat(embs)
- embeddings.append(embs.detach().numpy())
+ embeddings.append(embs.cpu().detach().numpy())
embeddings = np.concatenate(embeddings)
labels = cb_model(embeddings)
sv_output = postprocess(segments, vad_segments, labels, embeddings)
@@ -1238,37 +1254,6 @@
return cache
- #def _prepare_cache(cache: dict = {}, chunk_size=[5, 10, 5], batch_size=1):
- # if len(cache) > 0:
- # return cache
- # config = _read_yaml(asr_train_config)
- # enc_output_size = config["encoder_conf"]["output_size"]
- # feats_dims = config["frontend_conf"]["n_mels"] * config["frontend_conf"]["lfr_m"]
- # cache_en = {"start_idx": 0, "cif_hidden": torch.zeros((batch_size, 1, enc_output_size)),
- # "cif_alphas": torch.zeros((batch_size, 1)), "chunk_size": chunk_size, "last_chunk": False,
- # "feats": torch.zeros((batch_size, chunk_size[0] + chunk_size[2], feats_dims)), "tail_chunk": False}
- # cache["encoder"] = cache_en
-
- # cache_de = {"decode_fsmn": None}
- # cache["decoder"] = cache_de
-
- # return cache
-
- #def _cache_reset(cache: dict = {}, chunk_size=[5, 10, 5], batch_size=1):
- # if len(cache) > 0:
- # config = _read_yaml(asr_train_config)
- # enc_output_size = config["encoder_conf"]["output_size"]
- # feats_dims = config["frontend_conf"]["n_mels"] * config["frontend_conf"]["lfr_m"]
- # cache_en = {"start_idx": 0, "cif_hidden": torch.zeros((batch_size, 1, enc_output_size)),
- # "cif_alphas": torch.zeros((batch_size, 1)), "chunk_size": chunk_size, "last_chunk": False,
- # "feats": torch.zeros((batch_size, chunk_size[0] + chunk_size[2], feats_dims)),
- # "tail_chunk": False}
- # cache["encoder"] = cache_en
-
- # cache_de = {"decode_fsmn": None}
- # cache["decoder"] = cache_de
-
- # return cache
def _forward(
data_path_and_name_and_type,
--
Gitblit v1.9.1