├── .dockerignore ├── .github └── workflows │ └── docker-image.yml ├── .gitignore ├── Dockerfile ├── LICENSE ├── README.md ├── docker-compose.yml ├── example.jpg ├── example2.jpg ├── main.py └── requirements.txt /.dockerignore: -------------------------------------------------------------------------------- 1 | docker-compose.yml 2 | .gitignore 3 | README.md 4 | example.jpg 5 | .github -------------------------------------------------------------------------------- /.github/workflows/docker-image.yml: -------------------------------------------------------------------------------- 1 | name: Docker Image CI 2 | 3 | on: 4 | push: 5 | branches: [ "master" ] 6 | pull_request: 7 | branches: [ "master" ] 8 | 9 | jobs: 10 | 11 | build: 12 | 13 | runs-on: ubuntu-latest 14 | 15 | environment: production 16 | 17 | steps: 18 | - name: Checkout repository 19 | uses: actions/checkout@v2 20 | 21 | - name: Set up Docker Buildx 22 | uses: docker/setup-buildx-action@v2 23 | 24 | - name: Login to Docker Hub 25 | uses: docker/login-action@v2 26 | with: 27 | username: ${{ secrets.DOCKER_USER }} 28 | password: ${{ secrets.DOCKER_TOKEN }} 29 | 30 | - name: Get the current date 31 | id: date 32 | run: echo "DATE=$(date +'%Y-%m-%d')" >> $GITHUB_ENV 33 | 34 | - name: Extract repository name 35 | id: extract_repo_name 36 | run: echo "REPO_NAME=$(echo ${GITHUB_REPOSITORY} | cut -d'/' -f2)" >> $GITHUB_ENV 37 | 38 | - name: Build and push Docker image 39 | uses: docker/build-push-action@v4 40 | with: 41 | context: . 42 | push: true 43 | tags: ${{ secrets.DOCKER_USER }}/${{ env.REPO_NAME }}:latest 44 | 45 | - name: Logout from Docker Hub 46 | run: docker logout -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- 1 | .idea 2 | flagged 3 | sentence_transformers 4 | **/__pycache__/ -------------------------------------------------------------------------------- /Dockerfile: -------------------------------------------------------------------------------- 1 | # 使用官方的 Python 镜像作为基础镜像 2 | FROM pytorch/pytorch:2.3.1-cuda11.8-cudnn8-runtime 3 | 4 | # 设置工作目录 5 | WORKDIR /app 6 | 7 | # 复制依赖文件 8 | COPY requirements.txt requirements.txt 9 | 10 | # 安装 Python 依赖项 11 | RUN pip install --no-cache-dir -r requirements.txt 12 | 13 | # 复制当前目录中的文件到工作目录中 14 | COPY . . 15 | 16 | # 下载模型 17 | RUN python -c "from funasr import AutoModel; AutoModel(model='paraformer-zh',vad_model='fsmn-vad',punc_model='ct-punc')" 18 | 19 | # 暴露端口 20 | EXPOSE 12369 21 | 22 | # 启动 FastAPI 应用程序 23 | CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "12369"] -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- 1 | Apache License 2 | Version 2.0, January 2004 3 | http://www.apache.org/licenses/ 4 | 5 | TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION 6 | 7 | 1. Definitions. 8 | 9 | "License" shall mean the terms and conditions for use, reproduction, 10 | and distribution as defined by Sections 1 through 9 of this document. 11 | 12 | "Licensor" shall mean the copyright owner or entity authorized by 13 | the copyright owner that is granting the License. 14 | 15 | "Legal Entity" shall mean the union of the acting entity and all 16 | other entities that control, are controlled by, or are under common 17 | control with that entity. For the purposes of this definition, 18 | "control" means (i) the power, direct or indirect, to cause the 19 | direction or management of such entity, whether by contract or 20 | otherwise, or (ii) ownership of fifty percent (50%) or more of the 21 | outstanding shares, or (iii) beneficial ownership of such entity. 22 | 23 | "You" (or "Your") shall mean an individual or Legal Entity 24 | exercising permissions granted by this License. 25 | 26 | "Source" form shall mean the preferred form for making modifications, 27 | including but not limited to software source code, documentation 28 | source, and configuration files. 29 | 30 | "Object" form shall mean any form resulting from mechanical 31 | transformation or translation of a Source form, including but 32 | not limited to compiled object code, generated documentation, 33 | and conversions to other media types. 34 | 35 | "Work" shall mean the work of authorship, whether in Source or 36 | Object form, made available under the License, as indicated by a 37 | copyright notice that is included in or attached to the work 38 | (an example is provided in the Appendix below). 39 | 40 | "Derivative Works" shall mean any work, whether in Source or Object 41 | form, that is based on (or derived from) the Work and for which the 42 | editorial revisions, annotations, elaborations, or other modifications 43 | represent, as a whole, an original work of authorship. For the purposes 44 | of this License, Derivative Works shall not include works that remain 45 | separable from, or merely link (or bind by name) to the interfaces of, 46 | the Work and Derivative Works thereof. 47 | 48 | "Contribution" shall mean any work of authorship, including 49 | the original version of the Work and any modifications or additions 50 | to that Work or Derivative Works thereof, that is intentionally 51 | submitted to Licensor for inclusion in the Work by the copyright owner 52 | or by an individual or Legal Entity authorized to submit on behalf of 53 | the copyright owner. For the purposes of this definition, "submitted" 54 | means any form of electronic, verbal, or written communication sent 55 | to the Licensor or its representatives, including but not limited to 56 | communication on electronic mailing lists, source code control systems, 57 | and issue tracking systems that are managed by, or on behalf of, the 58 | Licensor for the purpose of discussing and improving the Work, but 59 | excluding communication that is conspicuously marked or otherwise 60 | designated in writing by the copyright owner as "Not a Contribution." 61 | 62 | "Contributor" shall mean Licensor and any individual or Legal Entity 63 | on behalf of whom a Contribution has been received by Licensor and 64 | subsequently incorporated within the Work. 65 | 66 | 2. Grant of Copyright License. Subject to the terms and conditions of 67 | this License, each Contributor hereby grants to You a perpetual, 68 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 69 | copyright license to reproduce, prepare Derivative Works of, 70 | publicly display, publicly perform, sublicense, and distribute the 71 | Work and such Derivative Works in Source or Object form. 72 | 73 | 3. Grant of Patent License. Subject to the terms and conditions of 74 | this License, each Contributor hereby grants to You a perpetual, 75 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 76 | (except as stated in this section) patent license to make, have made, 77 | use, offer to sell, sell, import, and otherwise transfer the Work, 78 | where such license applies only to those patent claims licensable 79 | by such Contributor that are necessarily infringed by their 80 | Contribution(s) alone or by combination of their Contribution(s) 81 | with the Work to which such Contribution(s) was submitted. If You 82 | institute patent litigation against any entity (including a 83 | cross-claim or counterclaim in a lawsuit) alleging that the Work 84 | or a Contribution incorporated within the Work constitutes direct 85 | or contributory patent infringement, then any patent licenses 86 | granted to You under this License for that Work shall terminate 87 | as of the date such litigation is filed. 88 | 89 | 4. Redistribution. You may reproduce and distribute copies of the 90 | Work or Derivative Works thereof in any medium, with or without 91 | modifications, and in Source or Object form, provided that You 92 | meet the following conditions: 93 | 94 | (a) You must give any other recipients of the Work or 95 | Derivative Works a copy of this License; and 96 | 97 | (b) You must cause any modified files to carry prominent notices 98 | stating that You changed the files; and 99 | 100 | (c) You must retain, in the Source form of any Derivative Works 101 | that You distribute, all copyright, patent, trademark, and 102 | attribution notices from the Source form of the Work, 103 | excluding those notices that do not pertain to any part of 104 | the Derivative Works; and 105 | 106 | (d) If the Work includes a "NOTICE" text file as part of its 107 | distribution, then any Derivative Works that You distribute must 108 | include a readable copy of the attribution notices contained 109 | within such NOTICE file, excluding those notices that do not 110 | pertain to any part of the Derivative Works, in at least one 111 | of the following places: within a NOTICE text file distributed 112 | as part of the Derivative Works; within the Source form or 113 | documentation, if provided along with the Derivative Works; or, 114 | within a display generated by the Derivative Works, if and 115 | wherever such third-party notices normally appear. The contents 116 | of the NOTICE file are for informational purposes only and 117 | do not modify the License. You may add Your own attribution 118 | notices within Derivative Works that You distribute, alongside 119 | or as an addendum to the NOTICE text from the Work, provided 120 | that such additional attribution notices cannot be construed 121 | as modifying the License. 122 | 123 | You may add Your own copyright statement to Your modifications and 124 | may provide additional or different license terms and conditions 125 | for use, reproduction, or distribution of Your modifications, or 126 | for any such Derivative Works as a whole, provided Your use, 127 | reproduction, and distribution of the Work otherwise complies with 128 | the conditions stated in this License. 129 | 130 | 5. Submission of Contributions. Unless You explicitly state otherwise, 131 | any Contribution intentionally submitted for inclusion in the Work 132 | by You to the Licensor shall be under the terms and conditions of 133 | this License, without any additional terms or conditions. 134 | Notwithstanding the above, nothing herein shall supersede or modify 135 | the terms of any separate license agreement you may have executed 136 | with Licensor regarding such Contributions. 137 | 138 | 6. Trademarks. This License does not grant permission to use the trade 139 | names, trademarks, service marks, or product names of the Licensor, 140 | except as required for reasonable and customary use in describing the 141 | origin of the Work and reproducing the content of the NOTICE file. 142 | 143 | 7. Disclaimer of Warranty. Unless required by applicable law or 144 | agreed to in writing, Licensor provides the Work (and each 145 | Contributor provides its Contributions) on an "AS IS" BASIS, 146 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or 147 | implied, including, without limitation, any warranties or conditions 148 | of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A 149 | PARTICULAR PURPOSE. You are solely responsible for determining the 150 | appropriateness of using or redistributing the Work and assume any 151 | risks associated with Your exercise of permissions under this License. 152 | 153 | 8. Limitation of Liability. In no event and under no legal theory, 154 | whether in tort (including negligence), contract, or otherwise, 155 | unless required by applicable law (such as deliberate and grossly 156 | negligent acts) or agreed to in writing, shall any Contributor be 157 | liable to You for damages, including any direct, indirect, special, 158 | incidental, or consequential damages of any character arising as a 159 | result of this License or out of the use or inability to use the 160 | Work (including but not limited to damages for loss of goodwill, 161 | work stoppage, computer failure or malfunction, or any and all 162 | other commercial damages or losses), even if such Contributor 163 | has been advised of the possibility of such damages. 164 | 165 | 9. Accepting Warranty or Additional Liability. While redistributing 166 | the Work or Derivative Works thereof, You may choose to offer, 167 | and charge a fee for, acceptance of support, warranty, indemnity, 168 | or other liability obligations and/or rights consistent with this 169 | License. However, in accepting such obligations, You may act only 170 | on Your own behalf and on Your sole responsibility, not on behalf 171 | of any other Contributor, and only if You agree to indemnify, 172 | defend, and hold each Contributor harmless for any liability 173 | incurred by, or claims asserted against, such Contributor by reason 174 | of your accepting any such warranty or additional liability. 175 | 176 | END OF TERMS AND CONDITIONS 177 | 178 | APPENDIX: How to apply the Apache License to your work. 179 | 180 | To apply the Apache License to your work, attach the following 181 | boilerplate notice, with the fields enclosed by brackets "[]" 182 | replaced with your own identifying information. (Don't include 183 | the brackets!) The text should be enclosed in the appropriate 184 | comment syntax for the file format. We also recommend that a 185 | file or class name and description of purpose be included on the 186 | same "printed page" as the copyright notice for easier 187 | identification within third-party archives. 188 | 189 | Copyright [yyyy] [name of copyright owner] 190 | 191 | Licensed under the Apache License, Version 2.0 (the "License"); 192 | you may not use this file except in compliance with the License. 193 | You may obtain a copy of the License at 194 | 195 | http://www.apache.org/licenses/LICENSE-2.0 196 | 197 | Unless required by applicable law or agreed to in writing, software 198 | distributed under the License is distributed on an "AS IS" BASIS, 199 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 200 | See the License for the specific language governing permissions and 201 | limitations under the License. 202 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # 语音转文字ASR工具 2 | 3 | 基于funasr开源项目和模型，快速搭建语音转文字的api服务 4 | 5 | ## 安装 6 | 7 | ### 方式一：本地python环境启动 8 | 9 | 安装所需软件包 10 | 11 | ``` 12 | pip install -i https://mirror.baidu.com/pypi/simple -r requirements.txt 13 | ``` 14 | 15 | 启动 16 | 17 | ``` 18 | python main.py 19 | ``` 20 | 21 | ### 方式二：docker-compose一键安装 22 | 23 | ``` 24 | docker-compose up -d 25 | ``` 26 | 27 | ## 相关接口 28 | 29 | 提供的接口：`POST` http://127.0.0.1:12369/asr 30 | - 支持mp3、wav音频文件转文字 31 | ![](example.jpg) 32 | - 支持mp4等视频文件转文字 33 | ![](example2.jpg) -------------------------------------------------------------------------------- /docker-compose.yml: -------------------------------------------------------------------------------- 1 | version: '3' 2 | 3 | services: 4 | app: 5 | image: dreamplay/hello_asr:latest 6 | ports: 7 | - 12369:12369 8 | restart: always 9 | volumes: 10 | - .:/app -------------------------------------------------------------------------------- /example.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/luler/hello_asr/09f75ac335ce47a99224eeea4c28dcad27525923/example.jpg -------------------------------------------------------------------------------- /example2.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/luler/hello_asr/09f75ac335ce47a99224eeea4c28dcad27525923/example2.jpg -------------------------------------------------------------------------------- /main.py: -------------------------------------------------------------------------------- 1 | import os 2 | import re 3 | import tempfile 4 | from typing import List 5 | 6 | import torch 7 | from fastapi import FastAPI, File, UploadFile, HTTPException 8 | from funasr import AutoModel 9 | 10 | app = FastAPI() 11 | 12 | device = "cuda" if torch.cuda.is_available() else "cpu" 13 | 14 | model = AutoModel( 15 | model="paraformer-zh", 16 | vad_model="fsmn-vad", 17 | vad_kwargs={"max_single_segment_time": 60000}, 18 | punc_model="ct-punc", 19 | device=device, 20 | # spk_model="cam++", 21 | ) 22 | 23 | 24 | def convert_audio(input_file): 25 | import ffmpeg 26 | 27 | output_file = input_file + ".wav" 28 | ( 29 | ffmpeg.input(input_file) 30 | .output(output_file) 31 | .run(quiet=True) 32 | ) 33 | return output_file 34 | 35 | 36 | # 异步函数，用于保存上传的文件到临时目录 37 | async def save_upload_file(upload_file: UploadFile) -> str: 38 | suffix = os.path.splitext(upload_file.filename)[1] # 获取文件后缀名 39 | with tempfile.NamedTemporaryFile(delete=False, suffix=suffix) as temp_file: # 创建临时文件 40 | temp_file.write(await upload_file.read()) # 将上传的文件内容写入临时文件 41 | return temp_file.name # 返回临时文件路径 42 | 43 | 44 | def funasr_to_srt(funasr_result): 45 | data = funasr_result 46 | text = data[0]['text'] 47 | timestamps = data[0]['timestamp'] 48 | 49 | # 配置参数 50 | max_chars_per_line = 20 # 每行字幕的最大字符数 51 | 52 | # 首先按照标点符号分割文本为短句 53 | sentence_pattern = r'([^，。！？,.!?;；、]+[，。！？,.!?;；、]+)' 54 | phrases = re.findall(sentence_pattern, text) 55 | 56 | # 如果没有找到短句，就把整个文本作为一个短句 57 | if not phrases: 58 | phrases = [text] 59 | 60 | # 确保所有文本都被包含 61 | remaining_text = text 62 | for phrase in phrases: 63 | remaining_text = remaining_text.replace(phrase, '', 1) 64 | if remaining_text.strip(): 65 | phrases.append(remaining_text.strip()) 66 | 67 | # 计算每个短句对应的时间戳 68 | phrase_timestamps = [] 69 | total_chars = len(text) 70 | 71 | char_index = 0 72 | for phrase in phrases: 73 | if not phrase.strip(): 74 | continue 75 | 76 | phrase_len = len(phrase) 77 | # 计算短句在整个文本中的比例 78 | start_ratio = char_index / total_chars 79 | end_ratio = (char_index + phrase_len) / total_chars 80 | 81 | start_idx = min(int(start_ratio * len(timestamps)), len(timestamps) - 1) 82 | end_idx = min(int(end_ratio * len(timestamps)), len(timestamps) - 1) 83 | 84 | if start_idx == end_idx: 85 | if end_idx < len(timestamps) - 1: 86 | end_idx += 1 87 | 88 | start_time = timestamps[start_idx][0] 89 | end_time = timestamps[end_idx][1] 90 | 91 | phrase_timestamps.append((phrase, start_time, end_time)) 92 | char_index += phrase_len 93 | 94 | # 合并短句为合适长度的字幕段落，只考虑字数限制 95 | text_segments = [] 96 | current_text = "" 97 | current_start = None 98 | current_end = None 99 | 100 | for phrase, start, end in phrase_timestamps: 101 | # 如果当前段落为空，直接添加 102 | if not current_text: 103 | current_text = phrase 104 | current_start = start 105 | current_end = end 106 | continue 107 | 108 | # 检查添加当前短句后是否会超出字数限制 109 | combined_text = current_text + phrase 110 | 111 | if len(combined_text) > max_chars_per_line: 112 | # 如果会超出限制，保存当前段落并开始新段落 113 | text_segments.append((current_text, current_start, current_end)) 114 | current_text = phrase 115 | current_start = start 116 | current_end = end 117 | else: 118 | # 否则合并短句 119 | current_text = combined_text 120 | current_end = end 121 | 122 | # 添加最后一个段落 123 | if current_text: 124 | text_segments.append((current_text, current_start, current_end)) 125 | 126 | # 生成SRT格式，去除每段末尾的标点符号 127 | srt = "" 128 | for i, (text, start, end) in enumerate(text_segments, 1): 129 | # 去除段落末尾的标点符号 130 | cleaned_text = re.sub(r'[，。！？,.!?;；、]+$', '', text) 131 | 132 | srt += f"{i}\n" 133 | srt += f"{format_timestamp(start)} --> {format_timestamp(end)}\n" 134 | srt += f"{cleaned_text.strip()}\n\n" 135 | 136 | return srt 137 | 138 | 139 | def format_timestamp(milliseconds): 140 | # 将毫秒转换为SRT格式的时间戳 141 | seconds, milliseconds = divmod(milliseconds, 1000) 142 | hours, seconds = divmod(seconds, 3600) 143 | minutes, seconds = divmod(seconds, 60) 144 | return f"{hours:02}:{minutes:02}:{seconds:02},{milliseconds:03}" 145 | 146 | 147 | @app.post("/asr") 148 | async def asr(file: List[UploadFile] = File(...)): 149 | temp_input_file_path = None 150 | try: 151 | if not file or any(f.filename == "" for f in file): 152 | raise Exception("No file was uploaded") 153 | if len(file) != 1: 154 | raise Exception("Only one file can be uploaded at a time") 155 | file = file[0] 156 | 157 | ext_name = os.path.splitext(file.filename)[1].strip('.') 158 | 159 | temp_input_file_path = await save_upload_file(file) # 保存上传的文件 160 | if ext_name not in ['wav', 'mp3']: 161 | # 如果不是音频文件,用ffmpeg转换为音频文件 162 | temp_input_file_path = convert_audio(temp_input_file_path) 163 | # raise Exception("Unsupported file extension") 164 | 165 | print(temp_input_file_path) 166 | 167 | result = model.generate( 168 | input=temp_input_file_path, 169 | batch_size_s=300, 170 | batch_size_threshold_s=60, 171 | # hotword='魔搭' 172 | ) 173 | 174 | try: 175 | srt = funasr_to_srt(result) 176 | result[0]['srt'] = srt 177 | except: 178 | print('srt convert fail') 179 | 180 | return {"result": result} # 返回识别结果 181 | except Exception as e: # 捕获其他异常 182 | raise HTTPException(status_code=500, detail=str(e)) 183 | finally: 184 | # 清理临时文件 185 | for temp_file in [temp_input_file_path]: 186 | if temp_file and os.path.exists(temp_file): # 检查路径是否存在 187 | os.remove(temp_file) # 删除文件 188 | 189 | 190 | if __name__ == "__main__": 191 | import uvicorn 192 | 193 | uvicorn.run(app, host="0.0.0.0", port=12369) # 运行FastAPI应用 194 | -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- 1 | uvicorn==0.27.* 2 | fastapi==0.110.* 3 | python-multipart==0.0.* 4 | ffmpeg==1.4 5 | ffmpeg-python==0.2.0 6 | 7 | funasr==1.1.* 8 | modelscope==1.18.* 9 | pydub==0.25.* 10 | onnx==1.16.* 11 | onnxruntime==1.19.* 12 | onnxconverter-common==1.14.* --------------------------------------------------------------------------------