From 2acd24f0158b2c86d2fb4e6f1134b67a1150500e Mon Sep 17 00:00:00 2001
From: jmwang66 <wangjiaming.wjm@alibaba-inc.com>
Date: 星期四, 29 二月 2024 17:14:59 +0800
Subject: [PATCH] update whisper lid (#1407)
---
README.md | 18 ++++++++----------
1 files changed, 8 insertions(+), 10 deletions(-)
diff --git a/README.md b/README.md
index 22c53da..91b9eda 100644
--- a/README.md
+++ b/README.md
@@ -66,7 +66,7 @@
## Model Zoo
FunASR has open-sourced a large number of pre-trained models on industrial data. You are free to use, copy, modify, and share FunASR models under the [Model License Agreement](./MODEL_LICENSE). Below are some representative models, for more models please refer to the [Model Zoo]().
-(Note: 馃 represents the Huggingface model zoo link, 猸� represents the ModelScope model zoo link)
+(Note: 猸� represents the ModelScope model zoo link, 馃 represents the Huggingface model zoo link)
| Model Name | Task Details | Training Data | Parameters |
@@ -105,10 +105,8 @@
from funasr import AutoModel
# paraformer-zh is a multi-functional asr model
# use vad, punc, spk or not as you need
-model = AutoModel(model="paraformer-zh", model_revision="v2.0.4",
- vad_model="fsmn-vad", vad_model_revision="v2.0.4",
- punc_model="ct-punc-c", punc_model_revision="v2.0.4",
- # spk_model="cam++", spk_model_revision="v2.0.2",
+model = AutoModel(model="paraformer-zh", vad_model="fsmn-vad", punc_model="ct-punc-c",
+ # spk_model="cam++",
)
res = model.generate(input=f"{model.model_path}/example/asr_example.wav",
batch_size_s=300,
@@ -125,7 +123,7 @@
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="v2.0.4")
+model = AutoModel(model="paraformer-zh-streaming")
import soundfile
import os
@@ -148,7 +146,7 @@
```python
from funasr import AutoModel
-model = AutoModel(model="fsmn-vad", model_revision="v2.0.4")
+model = AutoModel(model="fsmn-vad")
wav_file = f"{model.model_path}/example/asr_example.wav"
res = model.generate(input=wav_file)
print(res)
@@ -160,7 +158,7 @@
from funasr import AutoModel
chunk_size = 200 # ms
-model = AutoModel(model="fsmn-vad", model_revision="v2.0.4")
+model = AutoModel(model="fsmn-vad")
import soundfile
@@ -188,7 +186,7 @@
```python
from funasr import AutoModel
-model = AutoModel(model="ct-punc", model_revision="v2.0.4")
+model = AutoModel(model="ct-punc")
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)
```
@@ -196,7 +194,7 @@
```python
from funasr import AutoModel
-model = AutoModel(model="fa-zh", model_revision="v2.0.4")
+model = AutoModel(model="fa-zh")
wav_file = f"{model.model_path}/example/asr_example.wav"
text_file = f"{model.model_path}/example/text.txt"
res = model.generate(input=(wav_file, text_file), data_type=("sound", "text"))
--
Gitblit v1.9.1