Upload 9 files

app.py

@@ -1,30 +1,14 @@
-import git
-git.Repo.clone_from('https://github.com/reazon-research/ReazonSpeech', 'ReazonSpeech')
-import pip, site, importlib
-pip.main(['install', 'ReazonSpeech/pkg/nemo-asr'])
-importlib.reload(site)   
-
+import fn
 import gradio as gr
-from reazonspeech.nemo.asr import audio_from_path, load_model, transcribe
-
-model = None
-
-def speech_to_text(audio_file):
-    global model
 
-    if not model:
-        model = load_model()
+fn.load_model()
 
-    audio = audio_from_path(audio_file)
-    ret = transcribe(model, audio)
-
-    return ret.text
-    # ret.segments
-    # ret.subwords
-
-gr.Interface(
-    fn=speech_to_text,
+demo = gr.Interface(
+    fn=fn.speech_to_text,
     inputs=[
-        gr.Audio(source="upload", type="filepath"),
+        gr.Audio(sources="upload", type="filepath"),
         ],
-    outputs="text").launch()
+    outputs=["text", "text"])
+
+if __name__ == '__main__':
+    demo.launch()

fn.py

@@ -0,0 +1,19 @@
+import install
+from reazonspeech.nemo.asr import audio_from_path, load_model, transcribe
+
+model = None
+
+def speech_to_text(audio_file, _model_size = None):
+    global model
+
+    if not model:
+        model = load_model()
+
+    audio = audio_from_path(audio_file)
+    ret = transcribe(model, audio)
+
+    text_with_timestamps = ''
+    for segment in ret.segments:
+        text_with_timestamps += f"{segment.start_seconds:.2f}\t{segment.end_seconds:.2f}\t{segment.text}\n"
+
+    return ret.text, text_with_timestamps

install.bat

@@ -0,0 +1,56 @@
+@echo off
+
+rem -------------------------------------------
+rem NOT guaranteed to work on Windows
+
+set REPOS=https://huggingface.co/spaces/aka7774/reazonspeech
+set APPDIR=reazonspeech
+set VENV=venv
+
+rem -------------------------------------------
+
+set INSTALL_DIR=%~dp0
+cd /d %INSTALL_DIR%
+
+:git_clone
+set DL_URL=%REPOS%
+set DL_DST=%APPDIR%
+git clone %DL_URL% %APPDIR%
+if exist %DL_DST% goto install_python
+
+set DL_URL=https://github.com/git-for-windows/git/releases/download/v2.41.0.windows.3/PortableGit-2.41.0.3-64-bit.7z.exe
+set DL_DST=PortableGit-2.41.0.3-64-bit.7z.exe
+curl -L -o %DL_DST% %DL_URL%
+if not exist %DL_DST% bitsadmin /transfer dl %DL_URL% %DL_DST%
+%DL_DST% -y
+del %DL_DST%
+
+set GIT=%INSTALL_DIR%PortableGit\bin\git
+%GIT% clone %REPOS%
+
+:install_python
+set DL_URL=https://github.com/indygreg/python-build-standalone/releases/download/20240107/cpython-3.10.13+20240107-i686-pc-windows-msvc-shared-install_only.tar.gz
+set DL_DST="%INSTALL_DIR%python.tar.gz"
+curl -L -o %DL_DST% %DL_URL%
+if not exist %DL_DST% bitsadmin /transfer dl %DL_URL% %DL_DST%
+tar -xzf %DL_DST%
+
+set PYTHON=%INSTALL_DIR%python\python.exe
+set PATH=%PATH%;%INSTALL_DIR%python310\Scripts
+
+:install_venv
+cd %APPDIR%
+%PYTHON% -m venv %VENV%
+set PYTHON=%VENV%\Scripts\python.exe
+
+:install_pip
+set DL_URL=https://bootstrap.pypa.io/get-pip.py
+set DL_DST=%INSTALL_DIR%get-pip.py
+curl -o %DL_DST% %DL_URL%
+if not exist %DL_DST% bitsadmin /transfer dl %DL_URL% %DL_DST%
+%PYTHON% %DL_DST%
+
+%PYTHON% -m pip install gradio
+%PYTHON% -m pip install -r requirements.txt
+
+pause

install.py

@@ -0,0 +1,5 @@
+import git
+git.Repo.clone_from('https://github.com/reazon-research/ReazonSpeech', 'ReazonSpeech')
+import pip, site, importlib
+pip.main(['install', 'ReazonSpeech/pkg/nemo-asr'])
+importlib.reload(site)

main.py

@@ -0,0 +1,43 @@
+import os
+import sys
+import time
+import signal
+import psutil
+import io
+
+from fastapi import FastAPI, Request, status, Form, UploadFile
+from fastapi.staticfiles import StaticFiles
+from fastapi.middleware.cors import CORSMiddleware
+from pydantic import BaseModel, Field
+from fastapi.exceptions import RequestValidationError
+from fastapi.responses import JSONResponse
+
+import fn
+import gradio as gr
+from app import demo
+
+app = FastAPI()
+
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=['*'],
+    allow_credentials=True,
+    allow_methods=["*"],
+    allow_headers=["*"],
+)
+
+gr.mount_gradio_app(app, demo, path="/gradio")
+
+fn.load_model()
+
+@app.post("/transcribe")
+async def transcribe_audio(file: UploadFile = Form(...)):
+    try:
+        file_content = await file.read()
+        file_stream = io.BytesIO(file_content)
+
+		text_only, text_with_timestamps = speech_to_text(file_stream)
+
+        return {"transcription": text_only, "text_with_timestamps": text_with_timestamps}
+    except Exception as e:
+        return {"error": str(e)}

requirements.txt

@@ -1,2 +1,5 @@
+fastapi
+uvicorn
 Cython
 GitPython
+python-multipart

venv.sh

@@ -0,0 +1,7 @@
+#!/usr/bin/bash
+
+python3 -m venv venv
+curl -kL https://bootstrap.pypa.io/get-pip.py | venv/bin/python
+
+venv/bin/python -m pip install gradio
+venv/bin/python -m pip install -r requirements.txt