From 94f7bd079c78d6b7f9ab1961e991caa2a929b858 Mon Sep 17 00:00:00 2001
From: shixian.shi <shixian.shi@alibaba-inc.com>
Date: 星期一, 05 二月 2024 11:15:06 +0800
Subject: [PATCH] update preset_spk_num
---
funasr/auto/auto_model.py | 63 +++++++++++++++----------------
1 files changed, 31 insertions(+), 32 deletions(-)
diff --git a/funasr/auto/auto_model.py b/funasr/auto/auto_model.py
index 4d0f302..8007d6e 100644
--- a/funasr/auto/auto_model.py
+++ b/funasr/auto/auto_model.py
@@ -88,7 +88,8 @@
class AutoModel:
def __init__(self, **kwargs):
- tables.print()
+ if kwargs.get("disable_log", False):
+ tables.print()
model, kwargs = self.build_model(**kwargs)
@@ -120,9 +121,6 @@
if spk_mode not in ["default", "vad_segment", "punc_segment"]:
logging.error("spk_mode should be one of default, vad_segment and punc_segment.")
self.spk_mode = spk_mode
- self.preset_spk_num = kwargs.get("preset_spk_num", None)
- if self.preset_spk_num:
- logging.warning("Using preset speaker number: {}".format(self.preset_spk_num))
self.kwargs = kwargs
self.model = model
@@ -133,8 +131,6 @@
self.spk_model = spk_model
self.spk_kwargs = spk_kwargs
self.model_path = kwargs.get("model_path")
-
-
def build_model(self, **kwargs):
assert "model" in kwargs
@@ -145,7 +141,7 @@
set_all_random_seed(kwargs.get("seed", 0))
device = kwargs.get("device", "cuda")
- if not torch.cuda.is_available() or kwargs.get("ngpu", 0) == 0:
+ if not torch.cuda.is_available() or kwargs.get("ngpu", 1) == 0:
device = "cpu"
kwargs["batch_size"] = 1
kwargs["device"] = device
@@ -199,8 +195,6 @@
res = self.model(*args, kwargs)
return res
-
-
def generate(self, input, input_len=None, **cfg):
if self.vad_model is None:
return self.inference(input, input_len=input_len, **cfg)
@@ -231,7 +225,7 @@
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 isinstance(data_batch[0], torch.Tensor): # fbank
+ 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
@@ -260,7 +254,7 @@
time_escape_total += time_escape
if pbar:
- pbar.update(1)
+ # pbar.update(1)
pbar.set_description(f"rtf_avg: {time_escape_total/time_speech_total:0.3f}")
torch.cuda.empty_cache()
return asr_result_list
@@ -285,10 +279,10 @@
key_list, data_list = prepare_data_iterator(input, input_len=input_len, data_type=kwargs.get("data_type", None))
results_ret_list = []
- time_speech_total_all_samples = 0.0
+ time_speech_total_all_samples = 1e-6
beg_total = time.time()
- pbar_total = tqdm(colour="red", total=len(res) + 1, dynamic_ncols=True)
+ pbar_total = tqdm(colour="red", total=len(res), dynamic_ncols=True)
for i in range(len(res)):
key = res[i]["key"]
vadsegments = res[i]["value"]
@@ -310,14 +304,14 @@
batch_size_ms_cum = 0
beg_idx = 0
beg_asr_total = time.time()
- time_speech_total_per_sample = speech_lengths/16000 + 1e-6
+ time_speech_total_per_sample = speech_lengths/16000
time_speech_total_all_samples += time_speech_total_per_sample
- pbar_sample = tqdm(colour="blue", total=n + 1, dynamic_ncols=True)
+ # pbar_sample = tqdm(colour="blue", total=n, dynamic_ncols=True)
all_segments = []
for j, _ in enumerate(range(0, n)):
- pbar_sample.update(1)
+ # pbar_sample.update(1)
batch_size_ms_cum += (sorted_data[j][0][1] - sorted_data[j][0][0])
if j < n - 1 and (
batch_size_ms_cum + sorted_data[j + 1][0][1] - sorted_data[j + 1][0][0]) < batch_size and (
@@ -336,19 +330,19 @@
segments = sv_chunk(vad_segments)
all_segments.extend(segments)
speech_b = [i[2] for i in segments]
- spk_res = self.inference(speech_b, input_len=None, model=self.spk_model, kwargs=kwargs, **cfg)
+ spk_res = self.inference(speech_b, input_len=None, model=self.spk_model, kwargs=kwargs, disable_pbar=True, **cfg)
results[_b]['spk_embedding'] = spk_res[0]['spk_embedding']
beg_idx = end_idx
if len(results) < 1:
continue
results_sorted.extend(results)
- end_asr_total = time.time()
- time_escape_total_per_sample = end_asr_total - beg_asr_total
- pbar_sample.update(1)
- pbar_sample.set_description(f"rtf_avg_per_sample: {time_escape_total_per_sample / time_speech_total_per_sample:0.3f}, "
- f"time_speech_total_per_sample: {time_speech_total_per_sample: 0.3f}, "
- f"time_escape_total_per_sample: {time_escape_total_per_sample:0.3f}")
+ # end_asr_total = time.time()
+ # time_escape_total_per_sample = end_asr_total - beg_asr_total
+ # pbar_sample.update(1)
+ # pbar_sample.set_description(f"rtf_avg_per_sample: {time_escape_total_per_sample / time_speech_total_per_sample:0.3f}, "
+ # f"time_speech_total_per_sample: {time_speech_total_per_sample: 0.3f}, "
+ # f"time_escape_total_per_sample: {time_escape_total_per_sample:0.3f}")
restored_data = [0] * n
for j in range(n):
@@ -386,7 +380,7 @@
# step.3 compute punc model
if self.punc_model is not None:
self.punc_kwargs.update(cfg)
- punc_res = self.inference(result["text"], model=self.punc_model, kwargs=self.punc_kwargs, **cfg)
+ punc_res = self.inference(result["text"], model=self.punc_model, kwargs=self.punc_kwargs, disable_pbar=True, **cfg)
import copy; raw_text = copy.copy(result["text"])
result["text"] = punc_res[0]["text"]
@@ -394,7 +388,7 @@
if self.spk_model is not None:
all_segments = sorted(all_segments, key=lambda x: x[0])
spk_embedding = result['spk_embedding']
- labels = self.cb_model(spk_embedding.cpu(), oracle_num=self.preset_spk_num)
+ labels = self.cb_model(spk_embedding.cpu(), oracle_num=kwargs['preset_spk_num'])
del result['spk_embedding']
sv_output = postprocess(all_segments, None, labels, spk_embedding.cpu())
if self.spk_mode == 'vad_segment': # recover sentence_list
@@ -418,13 +412,18 @@
result["key"] = key
results_ret_list.append(result)
+ end_asr_total = time.time()
+ time_escape_total_per_sample = end_asr_total - beg_asr_total
pbar_total.update(1)
-
- pbar_total.update(1)
- end_total = time.time()
- time_escape_total_all_samples = end_total - beg_total
- pbar_total.set_description(f"rtf_avg_all_samples: {time_escape_total_all_samples / time_speech_total_all_samples:0.3f}, "
- f"time_speech_total_all_samples: {time_speech_total_all_samples: 0.3f}, "
- f"time_escape_total_all_samples: {time_escape_total_all_samples:0.3f}")
+ pbar_total.set_description(f"rtf_avg: {time_escape_total_per_sample / time_speech_total_per_sample:0.3f}, "
+ f"time_speech: {time_speech_total_per_sample: 0.3f}, "
+ f"time_escape: {time_escape_total_per_sample:0.3f}")
+
+
+ # end_total = time.time()
+ # time_escape_total_all_samples = end_total - beg_total
+ # print(f"rtf_avg_all: {time_escape_total_all_samples / time_speech_total_all_samples:0.3f}, "
+ # f"time_speech_all: {time_speech_total_all_samples: 0.3f}, "
+ # f"time_escape_all: {time_escape_total_all_samples:0.3f}")
return results_ret_list
--
Gitblit v1.9.1