From c9905b9be06e0a10806b895485916a9543ea5970 Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期五, 01 三月 2024 15:08:30 +0800
Subject: [PATCH] whisper
---
examples/industrial_data_pretraining/whisper/demo.py | 2 +-
funasr/download/name_maps_from_hub.py | 1 +
README_zh.md | 21 +++++++++++----------
README.md | 1 +
4 files changed, 14 insertions(+), 11 deletions(-)
diff --git a/README.md b/README.md
index 91b9eda..295cdc9 100644
--- a/README.md
+++ b/README.md
@@ -79,6 +79,7 @@
| fsmn-vad <br> ( [猸怾(https://modelscope.cn/models/damo/speech_fsmn_vad_zh-cn-16k-common-pytorch/summary) [馃](https://huggingface.co/funasr/fsmn-vad) ) | voice activity detection | 5000 hours, Mandarin and English | 0.4M |
| fa-zh <br> ( [猸怾(https://modelscope.cn/models/damo/speech_timestamp_prediction-v1-16k-offline/summary) [馃](https://huggingface.co/funasr/fa-zh) ) | timestamp prediction | 5000 hours, Mandarin | 38M |
| cam++ <br> ( [猸怾(https://modelscope.cn/models/iic/speech_campplus_sv_zh-cn_16k-common/summary) [馃](https://huggingface.co/funasr/campplus) ) | speaker verification/diarization | 5000 hours | 7.2M |
+| whisper-large-v2 <br> ([猸怾(https://www.modelscope.cn/models/iic/speech_whisper-large_asr_multilingual/summary) [馃]() ) | speech recognition, with timestamps, non-streaming | multilingual | 1G |
diff --git a/README_zh.md b/README_zh.md
index 086b2bc..73c4315 100644
--- a/README_zh.md
+++ b/README_zh.md
@@ -71,16 +71,17 @@
锛堟敞锛氣瓙 琛ㄧずModelScope妯″瀷浠撳簱閾炬帴锛岎煠� 琛ㄧずHuggingface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](https://huggingface.co/funasr/paraformer-tp) ) | 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-streaming <br> ( [猸怾(https://modelscope.cn/models/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online/summary) [馃](https://huggingface.co/funasr/paraformer-zh-streaming) ) | 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](https://huggingface.co/funasr/paraformer-en) ) | 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](https://huggingface.co/funasr/conformer-en) ) | 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](https://huggingface.co/funasr/ct-punc) ) | 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](https://huggingface.co/funasr/fsmn-vad) ) | 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](https://huggingface.co/funasr/fa-zh) ) | 瀛楃骇鍒椂闂存埑棰勬祴 | 50000灏忔椂锛屼腑鏂� | 38M |
-| cam++ <br> ( [猸怾(https://modelscope.cn/models/iic/speech_campplus_sv_zh-cn_16k-common/summary) [馃](https://huggingface.co/funasr/campplus) ) | 璇磋瘽浜虹‘璁�/鍒嗗壊 | 5000灏忔椂 | 7.2M |
+| 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](https://huggingface.co/funasr/paraformer-tp) ) | 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-streaming <br> ( [猸怾(https://modelscope.cn/models/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online/summary) [馃](https://huggingface.co/funasr/paraformer-zh-streaming) ) | 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](https://huggingface.co/funasr/paraformer-en) ) | 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](https://huggingface.co/funasr/conformer-en) ) | 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](https://huggingface.co/funasr/ct-punc) ) | 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](https://huggingface.co/funasr/fsmn-vad) ) | 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](https://huggingface.co/funasr/fa-zh) ) | 瀛楃骇鍒椂闂存埑棰勬祴 | 50000灏忔椂锛屼腑鏂� | 38M |
+| cam++ <br> ( [猸怾(https://modelscope.cn/models/iic/speech_campplus_sv_zh-cn_16k-common/summary) [馃](https://huggingface.co/funasr/campplus) ) | 璇磋瘽浜虹‘璁�/鍒嗗壊 | 5000灏忔椂 | 7.2M |
+| whisper-large-v2 <br> ([猸怾(https://www.modelscope.cn/models/iic/speech_whisper-large_asr_multilingual/summary) [馃]() ) | 璇煶璇嗗埆锛屽甫鏃堕棿鎴宠緭鍑猴紝闈炲疄鏃� | 澶氳瑷� | 1G |
<a name="蹇�熷紑濮�"></a>
diff --git a/examples/industrial_data_pretraining/whisper/demo.py b/examples/industrial_data_pretraining/whisper/demo.py
index 071b49b..f010ea2 100644
--- a/examples/industrial_data_pretraining/whisper/demo.py
+++ b/examples/industrial_data_pretraining/whisper/demo.py
@@ -9,5 +9,5 @@
model_revision="v2.0.4",
)
-res = model.generate(input="https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav")
+res = model.generate(input="https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav", language=None)
print(res)
diff --git a/funasr/download/name_maps_from_hub.py b/funasr/download/name_maps_from_hub.py
index bdcba35..fe493a7 100644
--- a/funasr/download/name_maps_from_hub.py
+++ b/funasr/download/name_maps_from_hub.py
@@ -8,6 +8,7 @@
"ct-punc-c": "damo/punc_ct-transformer_zh-cn-common-vocab272727-pytorch",
"fa-zh": "damo/speech_timestamp_prediction-v1-16k-offline",
"cam++": "damo/speech_campplus_sv_zh-cn_16k-common",
+ "whisper-large-v2": "iic/speech_whisper-large_asr_multilingual",
}
name_maps_hf = {
--
Gitblit v1.9.1