From 296d73f7d647f63032380d19ad4f4e261f995c55 Mon Sep 17 00:00:00 2001
From: shixian.shi <shixian.shi@alibaba-inc.com>
Date: 星期一, 15 一月 2024 20:47:16 +0800
Subject: [PATCH] update readme
---
README.md | 27 +++++++++++++--------------
1 files changed, 13 insertions(+), 14 deletions(-)
diff --git a/README.md b/README.md
index 311439d..a53ce4d 100644
--- a/README.md
+++ b/README.md
@@ -61,7 +61,6 @@
| paraformer-zh-spk <br> ( [猸怾(https://modelscope.cn/models/damo/speech_paraformer-large-vad-punc-spk_asr_nat-zh-cn/summary) [馃]() ) | speech recognition with speaker diarization, with timestamps, non-streaming | 60000 hours, Mandarin | 220M |
| <nobr>paraformer-zh-online <br> ( [猸怾(https://modelscope.cn/models/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online/summary) [馃]() )</nobr> | speech recognition, streaming | 60000 hours, Mandarin | 220M |
| paraformer-en <br> ( [猸怾(https://www.modelscope.cn/models/damo/speech_paraformer-large-vad-punc_asr_nat-en-16k-common-vocab10020/summary) [馃]() ) | speech recognition, with timestamps, non-streaming | 50000 hours, English | 220M |
-| paraformer-en-spk <br> ([猸怾()[馃]() ) | speech recognition with speaker diarization, non-streaming | Undo | Undo |
| conformer-en <br> ( [猸怾(https://modelscope.cn/models/damo/speech_conformer_asr-en-16k-vocab4199-pytorch/summary) [馃]() ) | speech recognition, non-streaming | 50000 hours, English | 220M |
| ct-punc <br> ( [猸怾(https://modelscope.cn/models/damo/punc_ct-transformer_cn-en-common-vocab471067-large/summary) [馃]() ) | punctuation restoration | 100M, Mandarin and English | 1.1G |
| fsmn-vad <br> ( [猸怾(https://modelscope.cn/models/damo/speech_fsmn_vad_zh-cn-16k-common-pytorch/summary) [馃]() ) | voice activity detection | 5000 hours, Mandarin and English | 0.4M |
@@ -90,12 +89,15 @@
### 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=64,
+ 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 +110,7 @@
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
@@ -132,7 +134,6 @@
from funasr import AutoModel
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)
print(res)
@@ -163,8 +164,7 @@
```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)
```
@@ -172,10 +172,9 @@
```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"
+text_file = f"{model.model_path}/example/text.txt"
res = model(input=(wav_file, text_file), data_type=("sound", "text"))
print(res)
```
--
Gitblit v1.9.1