From b7cb19b01a1454f7a1388e24dcd4e10fc654bd7c Mon Sep 17 00:00:00 2001
From: shixian.shi <shixian.shi@alibaba-inc.com>
Date: 星期二, 16 一月 2024 11:30:25 +0800
Subject: [PATCH] update demo, readme
---
README_zh.md | 18 ++++++++++++------
1 files changed, 12 insertions(+), 6 deletions(-)
diff --git a/README_zh.md b/README_zh.md
index 861e61c..dc20302 100644
--- a/README_zh.md
+++ b/README_zh.md
@@ -91,7 +91,7 @@
vad_model="fsmn-vad", vad_model_revision="v2.0.2", \
punc_model="ct-punc-c", punc_model_revision="v2.0.2", \
spk_model="cam++", spk_model_revision="v2.0.2")
-res = model(input=f"{model.model_path}/example/asr_example.wav",
+res = model.generate(input=f"{model.model_path}/example/asr_example.wav",
batch_size=64,
hotword='榄旀惌')
print(res)
@@ -121,7 +121,7 @@
for i in range(total_chunk_num):
speech_chunk = speech[i*chunk_stride:(i+1)*chunk_stride]
is_final = i == total_chunk_num - 1
- res = model(input=speech_chunk, cache=cache, is_final=is_final, chunk_size=chunk_size, encoder_chunk_look_back=encoder_chunk_look_back, decoder_chunk_look_back=decoder_chunk_look_back)
+ res = model.generate(input=speech_chunk, cache=cache, is_final=is_final, chunk_size=chunk_size, encoder_chunk_look_back=encoder_chunk_look_back, decoder_chunk_look_back=decoder_chunk_look_back)
print(res)
```
@@ -134,7 +134,7 @@
model = AutoModel(model="fsmn-vad", model_revision="v2.0.2")
wav_file = f"{model.model_path}/example/asr_example.wav"
-res = model(input=wav_file)
+res = model.generate(input=wav_file)
print(res)
```
@@ -156,7 +156,7 @@
for i in range(total_chunk_num):
speech_chunk = speech[i*chunk_stride:(i+1)*chunk_stride]
is_final = i == total_chunk_num - 1
- res = model(input=speech_chunk, cache=cache, is_final=is_final, chunk_size=chunk_size)
+ res = model.generate(input=speech_chunk, cache=cache, is_final=is_final, chunk_size=chunk_size)
if len(res[0]["value"]):
print(res)
```
@@ -167,7 +167,7 @@
model = AutoModel(model="ct-punc", model_revision="v2.0.2")
-res = model(input="閭ｄ粖澶╃殑浼氬氨鍒拌繖閲屽惂 happy new year 鏄庡勾瑙�")
+res = model.generate(input="閭ｄ粖澶╃殑浼氬氨鍒拌繖閲屽惂 happy new year 鏄庡勾瑙�")
print(res)
```
@@ -179,7 +179,7 @@
wav_file = f"{model.model_path}/example/asr_example.wav"
text_file = f"{model.model_path}/example/text.txt"
-res = model(input=(wav_file, text_file), data_type=("sound", "text"))
+res = model.generate(input=(wav_file, text_file), data_type=("sound", "text"))
print(res)
```
鏇村璇︾粏鐢ㄦ硶锛圼绀轰緥](examples/industrial_data_pretraining)锛�
@@ -242,4 +242,10 @@
pages={2063--2067},
doi={10.21437/Interspeech.2022-9996}
}
+@article{shi2023seaco,
+ author={Xian Shi and Yexin Yang and Zerui Li and Yanni Chen and Zhifu Gao and Shiliang Zhang},
+ title={{SeACo-Paraformer: A Non-Autoregressive ASR System with Flexible and Effective Hotword Customization Ability}},
+ year=2023,
+ journal={arXiv preprint arXiv:2308.03266(accepted by ICASSP2024)},
+}
```
--
Gitblit v1.9.1