From 19645da9e998581e6329d679bae968d0c45d1895 Mon Sep 17 00:00:00 2001
From: shixian.shi <shixian.shi@alibaba-inc.com>
Date: 星期一, 15 一月 2024 20:46:40 +0800
Subject: [PATCH] update readme
---
README_zh.md | 38 +++++++++++++++-----------------------
1 files changed, 15 insertions(+), 23 deletions(-)
diff --git a/README_zh.md b/README_zh.md
index 5a489ee..2da2171 100644
--- a/README_zh.md
+++ b/README_zh.md
@@ -86,12 +86,15 @@
### 闈炲疄鏃惰闊宠瘑鍒�
```python
from funasr import AutoModel
-
-model = AutoModel(model="paraformer-zh")
-# for the long duration wav, you could add vad model
-# model = AutoModel(model="paraformer-zh", vad_model="fsmn-vad", punc_model="ct-punc")
-
-res = model(input="asr_example_zh.wav", batch_size=64)
+# paraformer-zh is a multi-functional asr model
+# use vad, punc, spk or not as you need
+model = AutoModel(model="paraformer-zh", model_revision="v2.0.2", \
+ 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",
+ batch_size=64,
+ hotword='榄旀惌')
print(res)
```
娉細`model_hub`锛氳〃绀烘ā鍨嬩粨搴擄紝`ms`涓洪�夋嫨modelscope涓嬭浇锛宍hf`涓洪�夋嫨huggingface涓嬭浇銆�
@@ -105,7 +108,7 @@
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="paraformer-zh-streaming", model_revision="v2.0.0")
+model = AutoModel(model="paraformer-zh-streaming", model_revision="v2.0.2")
import soundfile
import os
@@ -119,13 +122,7 @@
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(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)
```
@@ -160,11 +157,7 @@
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(input=speech_chunk, cache=cache, is_final=is_final, chunk_size=chunk_size)
if len(res[0]["value"]):
print(res)
```
@@ -173,7 +166,7 @@
```python
from funasr import AutoModel
-model = AutoModel(model="ct-punc", model_revision="v2.0.1")
+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�")
print(res)
@@ -186,9 +179,8 @@
model = AutoModel(model="fa-zh", model_revision="v2.0.0")
wav_file = f"{model.model_path}/example/asr_example.wav"
-text_file = f"{model.model_path}/example/asr_example.wav"
-res = model(input=(wav_file, text_file),
- data_type=("sound", "text"))
+text_file = f"{model.model_path}/example/text.txt"
+res = model(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�
--
Gitblit v1.9.1