From 247c763286c780e3f1a849148528b12e15506721 Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期五, 12 一月 2024 09:52:25 +0800
Subject: [PATCH] funasr1.0 fsmn-vad streaming
---
funasr/bin/inference.py | 2 +-
examples/industrial_data_pretraining/paraformer/demo.py | 4 ++--
funasr/bin/train.py | 2 +-
setup.py | 2 +-
examples/industrial_data_pretraining/paraformer_streaming/demo.py | 2 +-
5 files changed, 6 insertions(+), 6 deletions(-)
diff --git a/examples/industrial_data_pretraining/paraformer/demo.py b/examples/industrial_data_pretraining/paraformer/demo.py
index 1f3b9a1..12b963f 100644
--- a/examples/industrial_data_pretraining/paraformer/demo.py
+++ b/examples/industrial_data_pretraining/paraformer/demo.py
@@ -5,7 +5,7 @@
from funasr import AutoModel
-model = AutoModel(model="damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch", model_revison="v2.0.0")
+model = AutoModel(model="damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch", model_revision="v2.0.0")
res = model(input="https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav")
print(res)
@@ -13,7 +13,7 @@
from funasr import AutoFrontend
-frontend = AutoFrontend(model="damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch", model_revison="v2.0.0")
+frontend = AutoFrontend(model="damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch", model_revision="v2.0.0")
fbanks = frontend(input="https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav", batch_size=2)
diff --git a/examples/industrial_data_pretraining/paraformer_streaming/demo.py b/examples/industrial_data_pretraining/paraformer_streaming/demo.py
index 6d464f2..b62cc29 100644
--- a/examples/industrial_data_pretraining/paraformer_streaming/demo.py
+++ b/examples/industrial_data_pretraining/paraformer_streaming/demo.py
@@ -9,7 +9,7 @@
encoder_chunk_look_back = 4 #number of chunks to lookback for encoder self-attention
decoder_chunk_look_back = 1 #number of encoder chunks to lookback for decoder cross-attention
-model = AutoModel(model="damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online", model_revison="v2.0.0")
+model = AutoModel(model="damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online", model_revision="v2.0.0")
cache = {}
res = model(input="https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav",
chunk_size=chunk_size,
diff --git a/funasr/bin/inference.py b/funasr/bin/inference.py
index 515170b..e239747 100644
--- a/funasr/bin/inference.py
+++ b/funasr/bin/inference.py
@@ -83,7 +83,7 @@
return key_list, data_list
-@hydra.main(config_name=None, version_base=None)
+@hydra.main(config_name=None)
def main_hydra(cfg: DictConfig):
def to_plain_list(cfg_item):
if isinstance(cfg_item, ListConfig):
diff --git a/funasr/bin/train.py b/funasr/bin/train.py
index af3e8af..1f896b7 100644
--- a/funasr/bin/train.py
+++ b/funasr/bin/train.py
@@ -23,7 +23,7 @@
from funasr.download.download_from_hub import download_model
from funasr.register import tables
-@hydra.main(config_name=None, version_base=None)
+@hydra.main(config_name=None)
def main_hydra(kwargs: DictConfig):
if kwargs.get("debug", False):
import pdb; pdb.set_trace()
diff --git a/setup.py b/setup.py
index ecd3d3d..f7e6ee6 100644
--- a/setup.py
+++ b/setup.py
@@ -40,7 +40,7 @@
"hdbscan",
"umap",
"jaconv",
- "hydra-core",
+ "hydra-core>=1.3.2",
],
# train: The modules invoked when training only.
"train": [
--
Gitblit v1.9.1