From bbbf17e4d97ff155049c424af4e96bfded9089b1 Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期二, 16 一月 2024 15:51:57 +0800
Subject: [PATCH] fix win bug
---
README_zh.md | 140 +++++++++++++++++++++++++++++++++++-----------
1 files changed, 107 insertions(+), 33 deletions(-)
diff --git a/README_zh.md b/README_zh.md
index 8eaffb6..57a6bbb 100644
--- a/README_zh.md
+++ b/README_zh.md
@@ -31,6 +31,10 @@
<a name="鏈�鏂板姩鎬�"></a>
## 鏈�鏂板姩鎬�
+- 2024/01/09: funasr绀惧尯杞欢鍖厀indows 2.0鐗堟湰鍙戝竷锛屾敮鎸佽蒋浠跺寘涓枃绂荤嚎鏂囦欢杞啓4.1銆佽嫳鏂囩绾挎枃浠惰浆鍐�1.2銆佷腑鏂囧疄鏃跺惉鍐欐湇鍔�1.6鐨勬渶鏂板姛鑳斤紝璇︾粏淇℃伅鍙傞槄([FunASR绀惧尯杞欢鍖厀indows鐗堟湰](https://www.modelscope.cn/models/damo/funasr-runtime-win-cpu-x64/summary))
+- 2024/01/03: 涓枃绂荤嚎鏂囦欢杞啓鏈嶅姟 4.0 鍙戝竷锛屾柊澧炴敮鎸�8k妯″瀷銆佷紭鍖栨椂闂存埑涓嶅尮閰嶉棶棰樺強澧炲姞鍙ュ瓙绾у埆鏃堕棿鎴炽�佷紭鍖栬嫳鏂囧崟璇峟st鐑瘝鏁堟灉銆佹敮鎸佽嚜鍔ㄥ寲閰嶇疆绾跨▼鍙傛暟锛屽悓鏃朵慨澶嶅凡鐭ョ殑crash闂鍙婂唴瀛樻硠婕忛棶棰橈紝璇︾粏淇℃伅鍙傞槄([涓�閿儴缃叉枃妗(runtime/readme_cn.md#涓枃绂荤嚎鏂囦欢杞啓鏈嶅姟cpu鐗堟湰))
+- 2024/01/03: 涓枃瀹炴椂璇煶鍚啓鏈嶅姟 1.6 鍙戝竷锛�2pass-offline妯″紡鏀寔Ngram璇█妯″瀷瑙ｇ爜銆亀fst鐑瘝锛屽悓鏃朵慨澶嶅凡鐭ョ殑crash闂鍙婂唴瀛樻硠婕忛棶棰橈紝璇︾粏淇℃伅鍙傞槄([涓�閿儴缃叉枃妗(runtime/readme_cn.md#涓枃瀹炴椂璇煶鍚啓鏈嶅姟cpu鐗堟湰))
+- 2024/01/03: 鑻辨枃绂荤嚎鏂囦欢杞啓鏈嶅姟 1.2 鍙戝竷锛屼慨澶嶅凡鐭ョ殑crash闂鍙婂唴瀛樻硠婕忛棶棰橈紝璇︾粏淇℃伅鍙傞槄([涓�閿儴缃叉枃妗(runtime/readme_cn.md#鑻辨枃绂荤嚎鏂囦欢杞啓鏈嶅姟cpu鐗堟湰))
- 2023/12/04: funasr绀惧尯杞欢鍖厀indows 1.0鐗堟湰鍙戝竷锛屾敮鎸佷腑鏂囩绾挎枃浠惰浆鍐欍�佽嫳鏂囩绾挎枃浠惰浆鍐欍�佷腑鏂囧疄鏃跺惉鍐欐湇鍔★紝璇︾粏淇℃伅鍙傞槄([FunASR绀惧尯杞欢鍖厀indows鐗堟湰](https://www.modelscope.cn/models/damo/funasr-runtime-win-cpu-x64/summary))
- 2023/11/08锛氫腑鏂囩绾挎枃浠惰浆鍐欐湇鍔�3.0 CPU鐗堟湰鍙戝竷锛屾柊澧炴爣鐐瑰ぇ妯″瀷銆丯gram璇█妯″瀷涓巜fst鐑瘝锛岃缁嗕俊鎭弬闃�([涓�閿儴缃叉枃妗(runtime/readme_cn.md#涓枃绂荤嚎鏂囦欢杞啓鏈嶅姟cpu鐗堟湰))
- 2023/10/17: 鑻辨枃绂荤嚎鏂囦欢杞啓鏈嶅姟涓�閿儴缃茬殑CPU鐗堟湰鍙戝竷锛岃缁嗕俊鎭弬闃�([涓�閿儴缃叉枃妗(runtime/readme_cn.md#鑻辨枃绂荤嚎鏂囦欢杞啓鏈嶅姟cpu鐗堟湰))
@@ -53,68 +57,132 @@
锛堟敞锛歔馃]()琛ㄧずHuggingface妯″瀷浠撳簱閾炬帴锛孾猸怾()琛ㄧずModelScope妯″瀷浠撳簱閾炬帴锛�
-| 妯″瀷鍚嶅瓧 | 浠诲姟璇︽儏 | 璁粌鏁版嵁 | 鍙傛暟閲� |
-|:---------------------------------------------------------------------------------------------------------------------------------------------------------------:|:------------------:|:------------:|:----:|
-| paraformer-zh <br> ([猸怾(https://www.modelscope.cn/models/damo/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch/summary) [馃]() ) | 璇煶璇嗗埆锛屽甫鏃堕棿鎴宠緭鍑猴紝闈炲疄鏃� | 60000灏忔椂锛屼腑鏂� | 220M |
-| paraformer-zh-spk <br> ( [猸怾(https://modelscope.cn/models/damo/speech_paraformer-large-vad-punc-spk_asr_nat-zh-cn/summary) [馃]() ) | 鍒嗚鑹茶闊宠瘑鍒紝甯︽椂闂存埑杈撳嚭锛岄潪瀹炴椂 | 60000灏忔椂锛屼腑鏂� | 220M |
-| paraformer-zh-online <br> ( [猸怾(https://modelscope.cn/models/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online/summary) [馃]() ) | 璇煶璇嗗埆锛屽疄鏃� | 60000灏忔椂锛屼腑鏂� | 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]() ) | 璇煶璇嗗埆锛岄潪瀹炴椂 | 50000灏忔椂锛岃嫳鏂� | 220M |
-| paraformer-en-spk <br> ([猸怾() [馃]() ) | 璇煶璇嗗埆锛岄潪瀹炴椂 | 50000灏忔椂锛岃嫳鏂� | 220M |
-| conformer-en <br> ( [猸怾(https://modelscope.cn/models/damo/speech_conformer_asr-en-16k-vocab4199-pytorch/summary) [馃]() ) | 璇煶璇嗗埆锛岄潪瀹炴椂 | 50000灏忔椂锛岃嫳鏂� | 220M |
-| ct-punc <br> ( [猸怾(https://modelscope.cn/models/damo/punc_ct-transformer_cn-en-common-vocab471067-large/summary) [馃]() ) | 鏍囩偣鎭㈠ | 100M锛屼腑鏂囦笌鑻辨枃 | 1.1G |
-| fsmn-vad <br> ( [猸怾(https://modelscope.cn/models/damo/speech_fsmn_vad_zh-cn-16k-common-pytorch/summary) [馃]() ) | 璇煶绔偣妫�娴嬶紝瀹炴椂 | 5000灏忔椂锛屼腑鏂囦笌鑻辨枃 | 0.4M |
-| fa-zh <br> ( [猸怾(https://modelscope.cn/models/damo/speech_timestamp_prediction-v1-16k-offline/summary) [馃]() ) | 瀛楃骇鍒椂闂存埑棰勬祴 | 50000灏忔椂锛屼腑鏂� | 38M |
+| 妯″瀷鍚嶅瓧 | 浠诲姟璇︽儏 | 璁粌鏁版嵁 | 鍙傛暟閲� |
+|:------------------------------------------------------------------------------------------------------------------------------------------------------------:|:------------------:|:------------:|:----:|
+| paraformer-zh <br> ([猸怾(https://www.modelscope.cn/models/damo/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch/summary) [馃]() ) | 璇煶璇嗗埆锛屽甫鏃堕棿鎴宠緭鍑猴紝闈炲疄鏃� | 60000灏忔椂锛屼腑鏂� | 220M |
+| paraformer-zh-spk <br> ( [猸怾(https://modelscope.cn/models/damo/speech_paraformer-large-vad-punc-spk_asr_nat-zh-cn/summary) [馃]() ) | 鍒嗚鑹茶闊宠瘑鍒紝甯︽椂闂存埑杈撳嚭锛岄潪瀹炴椂 | 60000灏忔椂锛屼腑鏂� | 220M |
+| paraformer-zh-streaming <br> ( [猸怾(https://modelscope.cn/models/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online/summary) [馃]() ) | 璇煶璇嗗埆锛屽疄鏃� | 60000灏忔椂锛屼腑鏂� | 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]() ) | 璇煶璇嗗埆锛岄潪瀹炴椂 | 50000灏忔椂锛岃嫳鏂� | 220M |
+| conformer-en <br> ( [猸怾(https://modelscope.cn/models/damo/speech_conformer_asr-en-16k-vocab4199-pytorch/summary) [馃]() ) | 璇煶璇嗗埆锛岄潪瀹炴椂 | 50000灏忔椂锛岃嫳鏂� | 220M |
+| ct-punc <br> ( [猸怾(https://modelscope.cn/models/damo/punc_ct-transformer_cn-en-common-vocab471067-large/summary) [馃]() ) | 鏍囩偣鎭㈠ | 100M锛屼腑鏂囦笌鑻辨枃 | 1.1G |
+| fsmn-vad <br> ( [猸怾(https://modelscope.cn/models/damo/speech_fsmn_vad_zh-cn-16k-common-pytorch/summary) [馃]() ) | 璇煶绔偣妫�娴嬶紝瀹炴椂 | 5000灏忔椂锛屼腑鏂囦笌鑻辨枃 | 0.4M |
+| fa-zh <br> ( [猸怾(https://modelscope.cn/models/damo/speech_timestamp_prediction-v1-16k-offline/summary) [馃]() ) | 瀛楃骇鍒椂闂存埑棰勬祴 | 50000灏忔椂锛屼腑鏂� | 38M |
<a name="蹇�熷紑濮�"></a>
## 蹇�熷紑濮�
-FunASR鏀寔鏁颁竾灏忔椂宸ヤ笟鏁版嵁璁粌鐨勬ā鍨嬬殑鎺ㄧ悊鍜屽井璋冿紝璇︾粏淇℃伅鍙互鍙傞槄锛圼modelscope_egs](https://alibaba-damo-academy.github.io/FunASR/en/modelscope_pipeline/quick_start.html)锛夛紱涔熸敮鎸佸鏈爣鍑嗘暟鎹泦妯″瀷鐨勮缁冨拰寰皟锛岃缁嗕俊鎭彲浠ュ弬闃咃紙[egs](https://alibaba-damo-academy.github.io/FunASR/en/academic_recipe/asr_recipe.html)锛夈��
涓嬮潰涓哄揩閫熶笂鎵嬫暀绋嬶紝娴嬭瘯闊抽锛圼涓枃](https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/vad_example.wav)锛孾鑻辨枃]()锛�
### 鍙墽琛屽懡浠よ
```shell
-funasr --model paraformer-zh asr_example_zh.wav
+funasr +model=paraformer-zh +vad_model="fsmn-vad" +punc_model="ct-punc" +input=asr_example_zh.wav
```
娉細鏀寔鍗曟潯闊抽鏂囦欢璇嗗埆锛屼篃鏀寔鏂囦欢鍒楄〃锛屽垪琛ㄤ负kaldi椋庢牸wav.scp锛歚wav_id wav_path`
### 闈炲疄鏃惰闊宠瘑鍒�
```python
-from funasr import infer
-
-p = infer(model="paraformer-zh", vad_model="fsmn-vad", punc_model="ct-punc", model_hub="ms")
-
-res = p("asr_example_zh.wav", batch_size_token=5000)
+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="v2.0.2", \
+ 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.generate(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�
### 瀹炴椂璇煶璇嗗埆
-```python
-from funasr import infer
-p = infer(model="paraformer-zh-streaming", model_hub="ms")
+```python
+from funasr import AutoModel
chunk_size = [0, 10, 5] #[0, 10, 5] 600ms, [0, 8, 4] 480ms
-param_dict = {"cache": dict(), "is_final": False, "chunk_size": chunk_size, "encoder_chunk_look_back": 4, "decoder_chunk_look_back": 1}
+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
-import torchaudio
-speech = torchaudio.load("asr_example_zh.wav")[0][0]
-speech_length = speech.shape[0]
+model = AutoModel(model="paraformer-zh-streaming", model_revision="v2.0.2")
-stride_size = chunk_size[1] * 960
-sample_offset = 0
-for sample_offset in range(0, speech_length, min(stride_size, speech_length - sample_offset)):
- param_dict["is_final"] = True if sample_offset + stride_size >= speech_length - 1 else False
- input = speech[sample_offset: sample_offset + stride_size]
- rec_result = p(input=input, param_dict=param_dict)
- print(rec_result)
+import soundfile
+import os
+
+wav_file = os.path.join(model.model_path, "example/asr_example.wav")
+speech, sample_rate = soundfile.read(wav_file)
+chunk_stride = chunk_size[1] * 960 # 600ms
+
+cache = {}
+total_chunk_num = int(len((speech)-1)/chunk_stride+1)
+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.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)
```
+
娉細`chunk_size`涓烘祦寮忓欢鏃堕厤缃紝`[0,10,5]`琛ㄧず涓婂睆瀹炴椂鍑哄瓧绮掑害涓篳10*60=600ms`锛屾湭鏉ヤ俊鎭负`5*60=300ms`銆傛瘡娆℃帹鐞嗚緭鍏ヤ负`600ms`锛堥噰鏍风偣鏁颁负`16000*0.6=960`锛夛紝杈撳嚭涓哄搴旀枃瀛楋紝鏈�鍚庝竴涓闊崇墖娈佃緭鍏ラ渶瑕佽缃甡is_final=True`鏉ュ己鍒惰緭鍑烘渶鍚庝竴涓瓧銆�
-鏇村璇︾粏鐢ㄦ硶锛圼鏂颁汉鏂囨。](https://alibaba-damo-academy.github.io/FunASR/en/funasr/quick_start_zh.html)锛�
+### 璇煶绔偣妫�娴嬶紙闈炲疄鏃讹級
+```python
+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.generate(input=wav_file)
+print(res)
+```
+
+### 璇煶绔偣妫�娴嬶紙瀹炴椂锛�
+```python
+from funasr import AutoModel
+
+chunk_size = 200 # ms
+model = AutoModel(model="fsmn-vad", model_revision="v2.0.2")
+
+import soundfile
+
+wav_file = f"{model.model_path}/example/vad_example.wav"
+speech, sample_rate = soundfile.read(wav_file)
+chunk_stride = int(chunk_size * sample_rate / 1000)
+
+cache = {}
+total_chunk_num = int(len((speech)-1)/chunk_stride+1)
+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.generate(input=speech_chunk, cache=cache, is_final=is_final, chunk_size=chunk_size)
+ if len(res[0]["value"]):
+ print(res)
+```
+
+### 鏍囩偣鎭㈠
+```python
+from funasr import AutoModel
+
+model = AutoModel(model="ct-punc", model_revision="v2.0.2")
+
+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)
+```
+
+### 鏃堕棿鎴抽娴�
+```python
+from funasr import AutoModel
+
+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/text.txt"
+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](https://github.com/alibaba-damo-academy/FunASR/tree/main/examples/industrial_data_pretraining)锛�
<a name="鏈嶅姟閮ㄧ讲"></a>
@@ -174,4 +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