From 55c09aeaa25b4bb88a50e09ba68fa6ff00a6d676 Mon Sep 17 00:00:00 2001
From: shixian.shi <shixian.shi@alibaba-inc.com>
Date: 星期一, 15 一月 2024 20:10:39 +0800
Subject: [PATCH] update readme, fix seaco bug
---
README.md | 21 ++++++++++++---------
1 files changed, 12 insertions(+), 9 deletions(-)
diff --git a/README.md b/README.md
index 311439d..05f6364 100644
--- a/README.md
+++ b/README.md
@@ -90,12 +90,15 @@
### Speech Recognition (Non-streaming)
```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=16,
+ hotword='榄旀惌')
print(res)
```
Note: `model_hub`: represents the model repository, `ms` stands for selecting ModelScope download, `hf` stands for selecting Huggingface download.
@@ -108,7 +111,7 @@
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
@@ -163,7 +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)
@@ -172,7 +175,7 @@
```python
from funasr import AutoModel
-model = AutoModel(model="fa-zh", model_revision="v2.0.0")
+model = AutoModel(model="fa-zh", model_revision="v2.0.2")
wav_file = f"{model.model_path}/example/asr_example.wav"
text_file = f"{model.model_path}/example/asr_example.wav"
--
Gitblit v1.9.1