speech_recognition/FunASR
1
0
Fork 0
mirror of https://github.com/modelscope/FunASR synced 2025-09-15 14:48:36 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

np fix bug

Browse Source
This commit is contained in:
游雁 2023-07-06 19:13:00 +08:00
parent 9321718b3a
commit 7a207808bc
9 changed files with 17 additions and 15 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
README_zh.md
View File

@ -92,7 +92,7 @@ pip3 install -U modelscope
#### python版本示例
支持实时流式语音识别，并且会用非流式模型进行纠错，输出文本带有标点。目前只支持单个client，如需多并发请参考c++版本服务部署SDK（[点击此处]()）
支持实时流式语音识别，并且会用非流式模型进行纠错，输出文本带有标点。目前只支持单个client，如需多并发请参考下方c++版本服务部署SDK
##### 服务端部署
```shell
@ -107,6 +107,7 @@ python funasr_wss_client.py --host "127.0.0.1" --port 10095 --mode 2pass --chunk
```
更多例子可以参考（[点击此处](https://alibaba-damo-academy.github.io/FunASR/en/runtime/websocket_python.html#id2)）
<a name="cpp版本示例"></a>
#### c++版本示例
目前已支持离线文件转写服务（CPU），支持上百路并发请求
@ -162,9 +163,9 @@ cd egs/aishell/paraformer
<a name="联系我们"></a>
## 联系我们
如果您在使用中遇到困难，可以通过一下方式联系我们
如果您在使用中遇到困难，可以通过以下方式联系我们
- email: [funasr@list.alibaba-inc.com](funasr@list.alibaba-inc.com)
- 邮件: [funasr@list.alibaba-inc.com](funasr@list.alibaba-inc.com)
| 钉钉群 | 微信 |
|:---------------------------------------------------------------------:|:-----------------------------------------------------:|

3
funasr/bin/asr_inference_launch.py
View File

@ -639,7 +639,8 @@ def inference_paraformer_vad_punc(
batch_size_token_ms = batch_size_token*60
if speech2text.device == "cpu":
batch_size_token_ms = 0
batch_size_token_ms = max(batch_size_token_ms, sorted_data[0][0][1] - sorted_data[0][0][0])
if len(sorted_data) > 0 and len(sorted_data[0]) > 0:
batch_size_token_ms = max(batch_size_token_ms, sorted_data[0][0][1] - sorted_data[0][0][0])
batch_size_token_ms_cum = 0
beg_idx = 0

2
funasr/bin/diar_infer.py
View File

@ -179,7 +179,7 @@ class Speech2DiarizationSOND:
@staticmethod
def seq2arr(seq, vec_dim=8):
def int2vec(x, vec_dim=8, dtype=np.int):
def int2vec(x, vec_dim=8, dtype=np.int32):
b = ('{:0' + str(vec_dim) + 'b}').format(x)
# little-endian order: lower bit first
return (np.array(list(b)[::-1]) == '1').astype(dtype)

4
funasr/models/encoder/rnn_encoder.py
View File

@ -46,12 +46,12 @@ class RNNEncoder(AbsEncoder):
raise ValueError(f"Not supported rnn_type={rnn_type}")
if subsample is None:
subsample = np.ones(num_layers + 1, dtype=np.int)
subsample = np.ones(num_layers + 1, dtype=np.int32)
else:
subsample = subsample[:num_layers]
# Append 1 at the beginning because the second or later is used
subsample = np.pad(
np.array(subsample, dtype=np.int),
np.array(subsample, dtype=np.int32),
[1, num_layers - len(subsample)],
mode="constant",
constant_values=1,

2
funasr/modules/data2vec/data_utils.py
View File

@ -105,7 +105,7 @@ def compute_mask_indices(
for length in sorted(lengths, reverse=True):
lens = np.fromiter(
(e - s if e - s >= length + min_space else 0 for s, e in parts),
np.int,
np.int32,
)
l_sum = np.sum(lens)
if l_sum == 0:

2
funasr/modules/frontends/mask_estimator.py
View File

@ -13,7 +13,7 @@ from funasr.modules.rnn.encoders import RNNP
class MaskEstimator(torch.nn.Module):
def __init__(self, type, idim, layers, units, projs, dropout, nmask=1):
super().__init__()
subsample = np.ones(layers + 1, dtype=np.int)
subsample = np.ones(layers + 1, dtype=np.int32)
typ = type.lstrip("vgg").rstrip("p")
if type[-1] == "p":

8
funasr/modules/nets_utils.py
View File

@ -407,7 +407,7 @@ def get_subsample(train_args, mode, arch):
elif mode == "mt" and arch == "rnn":
# +1 means input (+1) and layers outputs (train_args.elayer)
subsample = np.ones(train_args.elayers + 1, dtype=np.int)
subsample = np.ones(train_args.elayers + 1, dtype=np.int32)
logging.warning("Subsampling is not performed for machine translation.")
logging.info("subsample: " + " ".join([str(x) for x in subsample]))
return subsample
@ -417,7 +417,7 @@ def get_subsample(train_args, mode, arch):
or (mode == "mt" and arch == "rnn")
or (mode == "st" and arch == "rnn")
):
subsample = np.ones(train_args.elayers + 1, dtype=np.int)
subsample = np.ones(train_args.elayers + 1, dtype=np.int32)
if train_args.etype.endswith("p") and not train_args.etype.startswith("vgg"):
ss = train_args.subsample.split("_")
for j in range(min(train_args.elayers + 1, len(ss))):
@ -432,7 +432,7 @@ def get_subsample(train_args, mode, arch):
elif mode == "asr" and arch == "rnn_mix":
subsample = np.ones(
train_args.elayers_sd + train_args.elayers + 1, dtype=np.int
train_args.elayers_sd + train_args.elayers + 1, dtype=np.int32
)
if train_args.etype.endswith("p") and not train_args.etype.startswith("vgg"):
ss = train_args.subsample.split("_")
@ -451,7 +451,7 @@ def get_subsample(train_args, mode, arch):
elif mode == "asr" and arch == "rnn_mulenc":
subsample_list = []
for idx in range(train_args.num_encs):
subsample = np.ones(train_args.elayers[idx] + 1, dtype=np.int)
subsample = np.ones(train_args.elayers[idx] + 1, dtype=np.int32)
if train_args.etype[idx].endswith("p") and not train_args.etype[
idx
].startswith("vgg"):

2
funasr/utils/misc.py
View File

@ -12,7 +12,7 @@ def statistic_model_parameters(model, prefix=None):
return numel
def int2vec(x, vec_dim=8, dtype=np.int):
def int2vec(x, vec_dim=8, dtype=np.int32):
b = ('{:0' + str(vec_dim) + 'b}').format(x)
# little-endian order: lower bit first
return (np.array(list(b)[::-1]) == '1').astype(dtype)

2
funasr/version.txt
View File

@ -1 +1 @@
0.6.8
0.6.9