From 8b46df6c53dd0ebbf6d1ea2ebe46883482139593 Mon Sep 17 00:00:00 2001 From: pengzhendong <275331498@qq.com> Date: Fri, 19 Dec 2025 17:03:30 +0800 Subject: [PATCH] update language usage --- README.md | 70 +++++++++++++++++++++++++---------------------- README_zh.md | 77 ++++++++++++++++++++++++++++++---------------------- demo1.py | 7 ++++- model.py | 9 ++---- 4 files changed, 90 insertions(+), 73 deletions(-) diff --git a/README.md b/README.md index 4f45635..d30aa1d 100644 --- a/README.md +++ b/README.md @@ -25,11 +25,10 @@ Online Experience: -| Model Name | Task Details | Training Data | Parameters | -| :-------------------------------------------------------------------------------------------------------------------------------------------------------------: |:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------:| :----------------------------: | :--------: | -| Fun-ASR-Nano
([⭐](https://www.modelscope.cn/models/FunAudioLLM/Fun-ASR-Nano-2512) [🤗](https://huggingface.co/FunAudioLLM/Fun-ASR-Nano-2512)) | Speech recognition supports Chinese, English, and Japanese. Chinese includes support for 7 dialects (Wu, Cantonese, Min, Hakka, Gan, Xiang, Jin) and 26 regional accents (Henan, Shanxi, Hubei, Sichuan, Chongqing, Yunnan, Guizhou, Guangdong, Guangxi and more than 20 other regions). English and Japanese cover multiple regional accents. Additional features include lyric recognition and rap speech recognition. | Tens of millions of hours | 800M | -| Fun-ASR-MLT-Nano
([⭐](https://www.modelscope.cn/models/FunAudioLLM/Fun-ASR-MLT-Nano-2512) [🤗](https://huggingface.co/FunAudioLLM/Fun-ASR-MLT-Nano-2512)) | Speech recognition supports Chinese, English, Cantonese, Japanese, Korean, Vietnamese, Indonesian, Thai, Malay, Filipino, Arabic, Hindi, Bulgarian, Croatian, Czech, Danish, Dutch, Estonian, Finnish, Greek, Hungarian, Irish, Latvian, Lithuanian, Maltese, Polish, Portuguese, Romanian, Slovak, Slovenian, Swedish, and 31 languages in total. | Hundreds of thousands of hours | 800M | - +| Model Name | Task Details | Training Data | Parameters | +| :-------------------------------------------------------------------------------------------------------------------------------------------------------------: | :----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: | :----------------------------: | :--------: | +| Fun-ASR-Nano
([⭐](https://www.modelscope.cn/models/FunAudioLLM/Fun-ASR-Nano-2512) [🤗](https://huggingface.co/FunAudioLLM/Fun-ASR-Nano-2512)) | Speech recognition supports Chinese, English, and Japanese. Chinese includes support for 7 dialects (Wu, Cantonese, Min, Hakka, Gan, Xiang, Jin) and 26 regional accents (Henan, Shanxi, Hubei, Sichuan, Chongqing, Yunnan, Guizhou, Guangdong, Guangxi and more than 20 other regions). English and Japanese cover multiple regional accents. Additional features include lyric recognition and rap speech recognition. | Tens of millions of hours | 800M | +| Fun-ASR-MLT-Nano
([⭐](https://www.modelscope.cn/models/FunAudioLLM/Fun-ASR-MLT-Nano-2512) [🤗](https://huggingface.co/FunAudioLLM/Fun-ASR-MLT-Nano-2512)) | Speech recognition supports Chinese, English, Cantonese, Japanese, Korean, Vietnamese, Indonesian, Thai, Malay, Filipino, Arabic, Hindi, Bulgarian, Croatian, Czech, Danish, Dutch, Estonian, Finnish, Greek, Hungarian, Irish, Latvian, Lithuanian, Maltese, Polish, Portuguese, Romanian, Slovak, Slovenian, Swedish, and 31 languages in total. | Hundreds of thousands of hours | 800M | @@ -90,7 +89,12 @@ def main(): cache={}, batch_size=1, hotwords=["开放时间"], - language="zh", # auto, zh, en, ja + # 中文、英文、日文 for Fun-ASR-Nano-2512 + # 中文、英文、粤语、日文、韩文、越南语、印尼语、泰语、马来语、菲律宾语、阿拉伯语、 + # 印地语、保加利亚语、克罗地亚语、捷克语、丹麦语、荷兰语、爱沙尼亚语、芬兰语、希腊语、 + # 匈牙利语、爱尔兰语、拉脱维亚语、立陶宛语、马耳他语、波兰语、葡萄牙语、罗马尼亚语、 + # 斯洛伐克语、斯洛文尼亚语、瑞典语 for Fun-ASR-MLT-Nano-2512 + language="中文", itn=True, # or False ) text = res[0]["text"] @@ -149,37 +153,37 @@ We evaluated Fun-ASR against other state-of-the-art models on open-source benchm ### 1. Open-Source Dataset Performance (WER %) -| Test set | GLM-ASR-nano | GLM-ASR-nano* | Whisper-large-v3 | Seed-ASR | Seed-ASR* | Kimi-Audio | Step-Audio2 | FireRed-ASR | Fun-ASR-nano | Fun-ASR | -| :--- | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | -| **Model Size** | 1.5B | 1.5B | 1.6B | - | - | - | - | 1.1B | 0.8B | 7.7B | -| **OpenSource** | ✅ | ✅ | ✅ | ❌ | ❌ | ✅ | ✅ | ✅ | ✅ | ❌ | -| AIShell1 | 1.81 | 2.17 | 4.72 | 0.68 | 1.63 | 0.71 | 0.63 | 0.54 | 1.80 | 1.22 | -| AIShell2 | - | 3.47 | 4.68 | 2.27 | 2.76 | 2.86 | 2.10 | 2.58 | 2.75 | 2.39 | -| Fleurs-zh | - | 3.65 | 5.18 | 3.43 | 3.23 | 3.11 | 2.68 | 4.81 | 2.56 | 2.53 | -| Fleurs-en | 5.78 | 6.95 | 6.23 | 9.39 | 9.39 | 6.99 | 3.03 | 10.79 | 5.96 | 4.74 | -| Librispeech-clean | 2.00 | 2.17 | 1.86 | 1.58 | 2.8 | 1.32 | 1.17 | 1.84 | 1.76 | 1.51 | -| Librispeech-other | 4.19 | 4.43 | 3.43 | 2.84 | 5.69 | 2.63 | 2.42 | 4.52 | 4.33 | 3.03 | -| WenetSpeech Meeting | 6.73 | 8.21 | 18.39 | 5.69 | 7.07 | 6.24 | 4.75 | 4.95 | 6.60 | 6.17 | -| WenetSpeech Net | - | 6.33 | 11.89 | 4.66 | 4.84 | 6.45 | 4.67 | 4.94 | 6.01 | 5.46 | +| Test set | GLM-ASR-nano | GLM-ASR-nano\* | Whisper-large-v3 | Seed-ASR | Seed-ASR\* | Kimi-Audio | Step-Audio2 | FireRed-ASR | Fun-ASR-nano | Fun-ASR | +| :------------------ | :----------: | :------------: | :--------------: | :------: | :--------: | :--------: | :---------: | :---------: | :----------: | :-----: | +| **Model Size** | 1.5B | 1.5B | 1.6B | - | - | - | - | 1.1B | 0.8B | 7.7B | +| **OpenSource** | ✅ | ✅ | ✅ | ❌ | ❌ | ✅ | ✅ | ✅ | ✅ | ❌ | +| AIShell1 | 1.81 | 2.17 | 4.72 | 0.68 | 1.63 | 0.71 | 0.63 | 0.54 | 1.80 | 1.22 | +| AIShell2 | - | 3.47 | 4.68 | 2.27 | 2.76 | 2.86 | 2.10 | 2.58 | 2.75 | 2.39 | +| Fleurs-zh | - | 3.65 | 5.18 | 3.43 | 3.23 | 3.11 | 2.68 | 4.81 | 2.56 | 2.53 | +| Fleurs-en | 5.78 | 6.95 | 6.23 | 9.39 | 9.39 | 6.99 | 3.03 | 10.79 | 5.96 | 4.74 | +| Librispeech-clean | 2.00 | 2.17 | 1.86 | 1.58 | 2.8 | 1.32 | 1.17 | 1.84 | 1.76 | 1.51 | +| Librispeech-other | 4.19 | 4.43 | 3.43 | 2.84 | 5.69 | 2.63 | 2.42 | 4.52 | 4.33 | 3.03 | +| WenetSpeech Meeting | 6.73 | 8.21 | 18.39 | 5.69 | 7.07 | 6.24 | 4.75 | 4.95 | 6.60 | 6.17 | +| WenetSpeech Net | - | 6.33 | 11.89 | 4.66 | 4.84 | 6.45 | 4.67 | 4.94 | 6.01 | 5.46 | -> *Note: Seed-ASR\* results are evaluated using the official API on volcengine; GLM-ASR-nano\* results are evaluated using the open-source checkpoint.* +> _Note: Seed-ASR\* results are evaluated using the official API on volcengine; GLM-ASR-nano\* results are evaluated using the open-source checkpoint._ ### 2. Industry Dataset Performance (WER %) -| Test set | GLM-ASR-Nano | Whisper-large-v3 | Seed-ASR | FireRed-ASR | Kimi-Audio | Paraformer v2 | Fun-ASR-nano | Fun-ASR | -| :--- | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | -| **Model Size** | 1.5B | 1.6B | - | 1.1B | 8B | 0.2B | 0.8B | 7.7B | -| **OpenSource** | ✅ | ✅ | ❌ | ✅ | ✅ | ✅ | ✅ | ❌ | -| Nearfield | 16.95 | 16.58 | 7.20 | 10.10 | 9.02 | 8.11 | 7.79 | 6.31 | -| Farfield | 9.44 | 22.21 | 4.59 | 7.49 | 10.95 | 9.55 | 5.79 | 4.34 | -| Complex Background | 23.79 | 32.57 | 12.90 | 15.56 | 15.56 | 15.19 | 14.59 | 11.45 | -| English General | 16.47 | 18.56 | 15.65 | 21.62 | 18.12 | 19.48 | 15.28 | 13.73 | -| Opensource | 4.67 | 7.05 | 3.83 | 5.31 | 3.79 | 6.23 | 4.22 | 3.38 | -| Dialect | 54.21 | 66.14 | 29.45 | 52.82 | 71.94 | 41.16 | 28.18 | 15.21 | -| Accent | 19.78 | 36.03 | 10.23 | 14.05 | 27.20 | 17.80 | 12.90 | 10.31 | -| Lyrics | 46.56 | 54.82 | 30.26 | 42.87 | 65.18 | 50.14 | 30.85 | 21.00 | -| Hiphop | 43.32 | 46.56 | 29.46 | 33.88 | 57.25 | 43.79 | 30.87 | 28.58 | -| **Average** | **26.13** | **33.39** | **15.95** | **22.63** | **31.00** | **23.49** | **16.72** | **12.70** | +| Test set | GLM-ASR-Nano | Whisper-large-v3 | Seed-ASR | FireRed-ASR | Kimi-Audio | Paraformer v2 | Fun-ASR-nano | Fun-ASR | +| :----------------- | :----------: | :--------------: | :-------: | :---------: | :--------: | :-----------: | :----------: | :-------: | +| **Model Size** | 1.5B | 1.6B | - | 1.1B | 8B | 0.2B | 0.8B | 7.7B | +| **OpenSource** | ✅ | ✅ | ❌ | ✅ | ✅ | ✅ | ✅ | ❌ | +| Nearfield | 16.95 | 16.58 | 7.20 | 10.10 | 9.02 | 8.11 | 7.79 | 6.31 | +| Farfield | 9.44 | 22.21 | 4.59 | 7.49 | 10.95 | 9.55 | 5.79 | 4.34 | +| Complex Background | 23.79 | 32.57 | 12.90 | 15.56 | 15.56 | 15.19 | 14.59 | 11.45 | +| English General | 16.47 | 18.56 | 15.65 | 21.62 | 18.12 | 19.48 | 15.28 | 13.73 | +| Opensource | 4.67 | 7.05 | 3.83 | 5.31 | 3.79 | 6.23 | 4.22 | 3.38 | +| Dialect | 54.21 | 66.14 | 29.45 | 52.82 | 71.94 | 41.16 | 28.18 | 15.21 | +| Accent | 19.78 | 36.03 | 10.23 | 14.05 | 27.20 | 17.80 | 12.90 | 10.31 | +| Lyrics | 46.56 | 54.82 | 30.26 | 42.87 | 65.18 | 50.14 | 30.85 | 21.00 | +| Hiphop | 43.32 | 46.56 | 29.46 | 33.88 | 57.25 | 43.79 | 30.87 | 28.58 | +| **Average** | **26.13** | **33.39** | **15.95** | **22.63** | **31.00** | **23.49** | **16.72** | **12.70** |
diff --git a/README_zh.md b/README_zh.md index 97dd8af..9164d07 100644 --- a/README_zh.md +++ b/README_zh.md @@ -25,11 +25,10 @@ Fun-ASR 是通义实验室推出的端到端语音识别大模型，是基于数
-| 模型 | 介绍 | 训练数据 | 参数 | -|:--------------------------------------------------------------------------------------------------------------------------------------------------------------:| :-----------: | :--------: |:----:| -| Fun-ASR-Nano
([⭐](https://www.modelscope.cn/models/FunAudioLLM/Fun-ASR-Nano-2512) [🤗](https://huggingface.co/FunAudioLLM/Fun-ASR-Nano-2512)) | 支持中文、英文、日文。中文包含 7 种方言（吴语、粤语、闽语、客家话、赣语、湘语、晋语）及 26 种地域口音支持（河南、陕西、湖北、四川、重庆、云南、贵州、广东、广西、河北、天津、山东、安徽、南京、江苏、杭州、甘肃、宁夏）。英文、日文涵盖多种地域口音。额外功能包括歌词识别与说唱语音识别。 | 数千万小时 | 8 亿 | -| Fun-ASR-MLT-Nano
([⭐](https://www.modelscope.cn/models/FunAudioLLM/Fun-ASR-MLT-Nano-2512) [🤗](https://huggingface.co/FunAudioLLM/Fun-ASR-MLT-Nano-2512)) | 支持中文、英文、粤语、日文、韩文、越南语、印尼语、泰语、马来语、菲律宾语、阿拉伯语、印地语、保加利亚语、克罗地亚语、捷克语、丹麦语、荷兰语、爱沙尼亚语、芬兰语、希腊语、匈牙利语、爱尔兰语、拉脱维亚语、立陶宛语、马耳他语、波兰语、葡萄牙语、罗马尼亚语、斯洛伐克语、斯洛文尼亚语、瑞典语，共 31 种语言。 | 数十万小时 | 8 亿 | - +| 模型 | 介绍 | 训练数据 | 参数 | +| :-------------------------------------------------------------------------------------------------------------------------------------------------------------: | :--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: | :--------: | :--: | +| Fun-ASR-Nano
([⭐](https://www.modelscope.cn/models/FunAudioLLM/Fun-ASR-Nano-2512) [🤗](https://huggingface.co/FunAudioLLM/Fun-ASR-Nano-2512)) | 支持中文、英文、日文。中文包含 7 种方言（吴语、粤语、闽语、客家话、赣语、湘语、晋语）及 26 种地域口音支持（河南、陕西、湖北、四川、重庆、云南、贵州、广东、广西、河北、天津、山东、安徽、南京、江苏、杭州、甘肃、宁夏）。英文、日文涵盖多种地域口音。额外功能包括歌词识别与说唱语音识别。 | 数千万小时 | 8 亿 | +| Fun-ASR-MLT-Nano
([⭐](https://www.modelscope.cn/models/FunAudioLLM/Fun-ASR-MLT-Nano-2512) [🤗](https://huggingface.co/FunAudioLLM/Fun-ASR-MLT-Nano-2512)) | 支持中文、英文、粤语、日文、韩文、越南语、印尼语、泰语、马来语、菲律宾语、阿拉伯语、印地语、保加利亚语、克罗地亚语、捷克语、丹麦语、荷兰语、爱沙尼亚语、芬兰语、希腊语、匈牙利语、爱尔兰语、拉脱维亚语、立陶宛语、马耳他语、波兰语、葡萄牙语、罗马尼亚语、斯洛伐克语、斯洛文尼亚语、瑞典语，共 31 种语言。 | 数十万小时 | 8 亿 | @@ -85,7 +84,19 @@ def main(): ) wav_path = f"{model.model_path}/example/zh.mp3" - res = model.generate(input=[wav_path], cache={}, batch_size=1) + res = model.generate( + input=[wav_path], + cache={}, + batch_size=1, + hotwords=["开放时间"], + # 中文、英文、日文 for Fun-ASR-Nano-2512 + # 中文、英文、粤语、日文、韩文、越南语、印尼语、泰语、马来语、菲律宾语、阿拉伯语、 + # 印地语、保加利亚语、克罗地亚语、捷克语、丹麦语、荷兰语、爱沙尼亚语、芬兰语、希腊语、 + # 匈牙利语、爱尔兰语、拉脱维亚语、立陶宛语、马耳他语、波兰语、葡萄牙语、罗马尼亚语、 + # 斯洛伐克语、斯洛文尼亚语、瑞典语 for Fun-ASR-MLT-Nano-2512 + language="中文", + itn=True, # or False + ) text = res[0]["text"] print(text) @@ -142,37 +153,37 @@ if __name__ == "__main__": ### 1. 开源数据集性能 (WER %) -| Test set | GLM-ASR-nano | GLM-ASR-nano* | Whisper-large-v3 | Seed-ASR | Seed-ASR* | Kimi-Audio | Step-Audio2 | FireRed-ASR | Fun-ASR-nano | Fun-ASR | -| :--- | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | -| **Model Size** | 1.5B | 1.5B | 1.6B | - | - | - | - | 1.1B | 0.8B | 7.7B | -| **OpenSource** | ✅ | ✅ | ✅ | ❌ | ❌ | ✅ | ✅ | ✅ | ✅ | ❌ | -| AIShell1 | 1.81 | 2.17 | 4.72 | 0.68 | 1.63 | 0.71 | 0.63 | 0.54 | 1.80 | 1.22 | -| AIShell2 | - | 3.47 | 4.68 | 2.27 | 2.76 | 2.86 | 2.10 | 2.58 | 2.75 | 2.39 | -| Fleurs-zh | - | 3.65 | 5.18 | 3.43 | 3.23 | 3.11 | 2.68 | 4.81 | 2.56 | 2.53 | -| Fleurs-en | 5.78 | 6.95 | 6.23 | 9.39 | 9.39 | 6.99 | 3.03 | 10.79 | 5.96 | 4.74 | -| Librispeech-clean | 2.00 | 2.17 | 1.86 | 1.58 | 2.8 | 1.32 | 1.17 | 1.84 | 1.76 | 1.51 | -| Librispeech-other | 4.19 | 4.43 | 3.43 | 2.84 | 5.69 | 2.63 | 2.42 | 4.52 | 4.33 | 3.03 | -| WenetSpeech Meeting | 6.73 | 8.21 | 18.39 | 5.69 | 7.07 | 6.24 | 4.75 | 4.95 | 6.60 | 6.17 | -| WenetSpeech Net | - | 6.33 | 11.89 | 4.66 | 4.84 | 6.45 | 4.67 | 4.94 | 6.01 | 5.46 | +| Test set | GLM-ASR-nano | GLM-ASR-nano\* | Whisper-large-v3 | Seed-ASR | Seed-ASR\* | Kimi-Audio | Step-Audio2 | FireRed-ASR | Fun-ASR-nano | Fun-ASR | +| :------------------ | :----------: | :------------: | :--------------: | :------: | :--------: | :--------: | :---------: | :---------: | :----------: | :-----: | +| **Model Size** | 1.5B | 1.5B | 1.6B | - | - | - | - | 1.1B | 0.8B | 7.7B | +| **OpenSource** | ✅ | ✅ | ✅ | ❌ | ❌ | ✅ | ✅ | ✅ | ✅ | ❌ | +| AIShell1 | 1.81 | 2.17 | 4.72 | 0.68 | 1.63 | 0.71 | 0.63 | 0.54 | 1.80 | 1.22 | +| AIShell2 | - | 3.47 | 4.68 | 2.27 | 2.76 | 2.86 | 2.10 | 2.58 | 2.75 | 2.39 | +| Fleurs-zh | - | 3.65 | 5.18 | 3.43 | 3.23 | 3.11 | 2.68 | 4.81 | 2.56 | 2.53 | +| Fleurs-en | 5.78 | 6.95 | 6.23 | 9.39 | 9.39 | 6.99 | 3.03 | 10.79 | 5.96 | 4.74 | +| Librispeech-clean | 2.00 | 2.17 | 1.86 | 1.58 | 2.8 | 1.32 | 1.17 | 1.84 | 1.76 | 1.51 | +| Librispeech-other | 4.19 | 4.43 | 3.43 | 2.84 | 5.69 | 2.63 | 2.42 | 4.52 | 4.33 | 3.03 | +| WenetSpeech Meeting | 6.73 | 8.21 | 18.39 | 5.69 | 7.07 | 6.24 | 4.75 | 4.95 | 6.60 | 6.17 | +| WenetSpeech Net | - | 6.33 | 11.89 | 4.66 | 4.84 | 6.45 | 4.67 | 4.94 | 6.01 | 5.46 | -> *注：Seed-ASR\* 结果使用 volcengine 上的官方 API 评估；GLM-ASR-nano\* 结果使用开源 checkpoint 评估。* +> _注：Seed-ASR\* 结果使用 volcengine 上的官方 API 评估；GLM-ASR-nano\* 结果使用开源 checkpoint 评估。_ ### 2. 工业数据集性能 (WER %) -| Test set | GLM-ASR-Nano | Whisper-large-v3 | Seed-ASR | FireRed-ASR | Kimi-Audio | Paraformer v2 | Fun-ASR-nano | Fun-ASR | -| :--- | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | -| **Model Size** | 1.5B | 1.6B | - | 1.1B | 8B | 0.2B | 0.8B | 7.7B | -| **OpenSource** | ✅ | ✅ | ❌ | ✅ | ✅ | ✅ | ✅ | ❌ | -| Nearfield | 16.95 | 16.58 | 7.20 | 10.10 | 9.02 | 8.11 | 7.79 | 6.31 | -| Farfield | 9.44 | 22.21 | 4.59 | 7.49 | 10.95 | 9.55 | 5.79 | 4.34 | -| Complex Background | 23.79 | 32.57 | 12.90 | 15.56 | 15.56 | 15.19 | 14.59 | 11.45 | -| English General | 16.47 | 18.56 | 15.65 | 21.62 | 18.12 | 19.48 | 15.28 | 13.73 | -| Opensource | 4.67 | 7.05 | 3.83 | 5.31 | 3.79 | 6.23 | 4.22 | 3.38 | -| Dialect | 54.21 | 66.14 | 29.45 | 52.82 | 71.94 | 41.16 | 28.18 | 15.21 | -| Accent | 19.78 | 36.03 | 10.23 | 14.05 | 27.20 | 17.80 | 12.90 | 10.31 | -| Lyrics | 46.56 | 54.82 | 30.26 | 42.87 | 65.18 | 50.14 | 30.85 | 21.00 | -| Hiphop | 43.32 | 46.56 | 29.46 | 33.88 | 57.25 | 43.79 | 30.87 | 28.58 | -| **Average** | **26.13** | **33.39** | **15.95** | **22.63** | **31.00** | **23.49** | **16.72** | **12.70** | +| Test set | GLM-ASR-Nano | Whisper-large-v3 | Seed-ASR | FireRed-ASR | Kimi-Audio | Paraformer v2 | Fun-ASR-nano | Fun-ASR | +| :----------------- | :----------: | :--------------: | :-------: | :---------: | :--------: | :-----------: | :----------: | :-------: | +| **Model Size** | 1.5B | 1.6B | - | 1.1B | 8B | 0.2B | 0.8B | 7.7B | +| **OpenSource** | ✅ | ✅ | ❌ | ✅ | ✅ | ✅ | ✅ | ❌ | +| Nearfield | 16.95 | 16.58 | 7.20 | 10.10 | 9.02 | 8.11 | 7.79 | 6.31 | +| Farfield | 9.44 | 22.21 | 4.59 | 7.49 | 10.95 | 9.55 | 5.79 | 4.34 | +| Complex Background | 23.79 | 32.57 | 12.90 | 15.56 | 15.56 | 15.19 | 14.59 | 11.45 | +| English General | 16.47 | 18.56 | 15.65 | 21.62 | 18.12 | 19.48 | 15.28 | 13.73 | +| Opensource | 4.67 | 7.05 | 3.83 | 5.31 | 3.79 | 6.23 | 4.22 | 3.38 | +| Dialect | 54.21 | 66.14 | 29.45 | 52.82 | 71.94 | 41.16 | 28.18 | 15.21 | +| Accent | 19.78 | 36.03 | 10.23 | 14.05 | 27.20 | 17.80 | 12.90 | 10.31 | +| Lyrics | 46.56 | 54.82 | 30.26 | 42.87 | 65.18 | 50.14 | 30.85 | 21.00 | +| Hiphop | 43.32 | 46.56 | 29.46 | 33.88 | 57.25 | 43.79 | 30.87 | 28.58 | +| **Average** | **26.13** | **33.39** | **15.95** | **22.63** | **31.00** | **23.49** | **16.72** | **12.70** |
diff --git a/demo1.py b/demo1.py index bc0cc02..5f8a67e 100644 --- a/demo1.py +++ b/demo1.py @@ -22,7 +22,12 @@ def main(): cache={}, batch_size=1, hotwords=["开放时间"], - language="zh", # auto, zh, en, ja + # 中文、英文、日文 for Fun-ASR-Nano-2512 + # 中文、英文、粤语、日文、韩文、越南语、印尼语、泰语、马来语、菲律宾语、阿拉伯语、 + # 印地语、保加利亚语、克罗地亚语、捷克语、丹麦语、荷兰语、爱沙尼亚语、芬兰语、希腊语、 + # 匈牙利语、爱尔兰语、拉脱维亚语、立陶宛语、马耳他语、波兰语、葡萄牙语、罗马尼亚语、 + # 斯洛伐克语、斯洛文尼亚语、瑞典语 for Fun-ASR-MLT-Nano-2512 + language="中文", itn=True, # or False ) text = res[0]["text"] diff --git a/model.py b/model.py index 06421c3..f8c05c8 100644 --- a/model.py +++ b/model.py @@ -552,14 +552,11 @@ class FunASRNano(nn.Module): prompt += f"热词列表：[{hotwords}]\n" else: prompt = "" - language = kwargs.get("language", "auto") - if language not in ("auto", "zh", "en", "ja"): - language = "auto" - if language == "auto": + language = kwargs.get("language", None) + if language is None: prompt += "语音转写" else: - LANGUAGE_MAP = {"zh": "中文", "en": "英文", "ja": "日文"} - prompt += f"语音转写成{LANGUAGE_MAP[language]}" + prompt += f"语音转写成{language}" itn = kwargs.get("itn", True) if not itn: prompt += "，不进行文本规整"