initial commit

.dockerignore

@@ -0,0 +1,34 @@
+# Include any files or directories that you don't want to be copied to your
+# container here (e.g., local build artifacts, temporary files, etc.).
+#
+# For more help, visit the .dockerignore file reference guide at
+# https://docs.docker.com/go/build-context-dockerignore/
+
+**/.DS_Store
+**/__pycache__
+**/.venv
+**/.classpath
+**/.dockerignore
+**/.env
+**/.git
+**/.gitignore
+**/.project
+**/.settings
+**/.toolstarget
+**/.vs
+**/.vscode
+**/*.*proj.user
+**/*.dbmdl
+**/*.jfm
+**/bin
+**/charts
+**/docker-compose*
+**/compose*
+**/Dockerfile*
+**/node_modules
+**/npm-debug.log
+**/obj
+**/secrets.dev.yaml
+**/values.dev.yaml
+LICENSE
+README.md

.gitignore

@@ -0,0 +1,22 @@
+# Build Artifacts
+build/
+
+# Core Dumps
+core
+
+# Byte-Compiled Modules
+__pycache__/
+
+# Extension Modules
+*.so
+
+# Packaging Artifacts
+*.egg-info
+*.whl
+
+# IDEs and Tools
+.idea/
+.gdb_history
+.vscode/
+# Other
+.DS_Store

Dockerfile

@@ -0,0 +1,43 @@
+FROM nvidia/cuda:12.1.0-cudnn8-devel-ubuntu20.04
+LABEL maintainer="Hugging Face"
+
+ARG DEBIAN_FRONTEND=noninteractive
+
+RUN apt update
+RUN apt install -y git libsndfile1-dev tesseract-ocr espeak-ng python3 python3-pip ffmpeg
+RUN python3 -m pip install --no-cache-dir --upgrade pip
+# RUN apt-get install -y git libsndfile1-dev tesseract-ocr espeak-ng ffmpeg
+# Prevents Python from writing pyc files.
+ENV PYTHONDONTWRITEBYTECODE=1
+ENV OMP_NUM_THREADS=1
+
+# Keeps Python from buffering stdout and stderr to avoid situations where
+# the application crashes without emitting any logs due to buffering.
+ENV PYTHONUNBUFFERED=1
+
+# ENV HF_HUB_CACHE="/hub"
+
+WORKDIR /app
+
+# Create a non-privileged user that the app will run under.
+# See https://docs.docker.com/go/dockerfile-user-best-practices/
+RUN useradd -m -u 1000 user
+# Download dependencies as a separate step to take advantage of Docker's caching.
+# Leverage a cache mount to /root/.cache/pip to speed up subsequent builds.
+# Leverage a bind mount to requirements.txt to avoid having to copy them into
+# into this layer.
+RUN --mount=type=cache,target=/root/.cache/pip \
+  --mount=type=bind,source=requirements.txt,target=requirements.txt \
+  python3 -m pip install -r requirements.txt
+
+# Switch to the non-privileged user to run the application.
+USER user
+
+# Copy the source code into the container.
+COPY . .
+
+# Expose the port that the application listens on.
+EXPOSE 8088
+
+# Run the application.
+CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "7860"]

README.Docker.md

@@ -0,0 +1,22 @@
+### Building and running your application
+
+When you're ready, start your application by running:
+`docker compose up --build`.
+
+Your application will be available at http://localhost:8088.
+
+### Deploying your application to the cloud
+
+First, build your image, e.g.: `docker build -t myapp .`.
+If your cloud uses a different CPU architecture than your development
+machine (e.g., you are on a Mac M1 and your cloud provider is amd64),
+you'll want to build the image for that platform, e.g.:
+`docker build --platform=linux/amd64 -t myapp .`.
+
+Then, push it to your registry, e.g. `docker push myregistry.com/myapp`.
+
+Consult Docker's [getting started](https://docs.docker.com/go/get-started-sharing/)
+docs for more detail on building and pushing.
+
+### References
+* [Docker's Python guide](https://docs.docker.com/language/python/)

README.md

@@ -1,10 +1,46 @@
 ---
-title: Transcribe
-emoji: 👁
-colorFrom: blue
+title: Whisper
+emoji: 🚀
+colorFrom: indigo
 colorTo: indigo
 sdk: docker
 pinned: false
+license: apache-2.0
 ---
 
+# Whisper
+
+## TODO
+
+- Use volumes cache export HF_DATASETS_CACHE="/path/to/another/directory"
+
 Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+
+mac book pro CPU
+9.87 sec
+9.51 sec
+
+CPU free
+29.15 sec
+29.97 sec
+28.38 sec
+
+T4 small
+1.127 sec
+1.058 sec
+1.054 sec
+
+A10g small
+0.92 sec
+0.90 sec
+0.94 sec
+0.89 sec
+
+OpenAI
+1.027
+1.297
+1.904
+1.303
+1.509
+1.870
+1.587

compose.yaml

@@ -0,0 +1,51 @@
+# Comments are provided throughout this file to help you get started.
+# If you need more help, visit the Docker compose reference guide at
+# https://docs.docker.com/go/compose-spec-reference/
+
+# Here the instructions define your application as a service called "server".
+# This service is built from the Dockerfile in the current directory.
+# You can add other services your application may depend on here, such as a
+# database or a cache. For examples, see the Awesome Compose repository:
+# https://github.com/docker/awesome-compose
+services:
+  server:
+    build:
+      context: .
+    ports:
+      - 8088:7860
+    volumes:
+      - /Users/hugorodrigues/Projects/AI/HF/whisper:/app:rw
+
+# The commented out section below is an example of how to define a PostgreSQL
+# database that your application can use. `depends_on` tells Docker Compose to
+# start the database before your application. The `db-data` volume persists the
+# database data between container restarts. The `db-password` secret is used
+# to set the database password. You must create `db/password.txt` and add
+# a password of your choosing to it before running `docker compose up`.
+#     depends_on:
+#       db:
+#         condition: service_healthy
+#   db:
+#     image: postgres
+#     restart: always
+#     user: postgres
+#     secrets:
+#       - db-password
+#     volumes:
+#       - db-data:/var/lib/postgresql/data
+#     environment:
+#       - POSTGRES_DB=example
+#       - POSTGRES_PASSWORD_FILE=/run/secrets/db-password
+#     expose:
+#       - 5432
+#     healthcheck:
+#       test: [ "CMD", "pg_isready" ]
+#       interval: 10s
+#       timeout: 5s
+#       retries: 5
+# volumes:
+#   db-data:
+# secrets:
+#   db-password:
+#     file: db/password.txt
+

main.py

@@ -0,0 +1,54 @@
+import time
+
+from fastapi import FastAPI, UploadFile
+from fastapi.middleware.cors import CORSMiddleware
+
+
+import torch
+from transformers import pipeline
+
+app = FastAPI(docs_url="/api/docs")
+
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=["*"],
+    allow_methods=["*"],
+    allow_headers=["*"],
+    allow_credentials=True,
+)
+
+device = "cuda:0" if torch.cuda.is_available() else "cpu"
+torch_dtype = torch.float16 if torch.cuda.is_available() else torch.float32
+
+BATCH_SIZE = 8
+
+
+pipe = pipeline("automatic-speech-recognition",
+                "openai/whisper-large-v3",
+                torch_dtype=torch_dtype,
+                device=device)
+
+
+@app.get("/device")
+def getDevice():
+    start_time = time.time()
+    print("Time took to process the request and return response is {} sec".format(
+        time.time() - start_time))
+    return device
+
+
+@app.post("/transcribe")
+def transcribe(soundFile: UploadFile, task="transcribe"):
+    start_time = time.time()
+
+    if soundFile is None:
+        raise "No audio file submitted! Please upload or record an audio file before submitting your request."
+
+    inputFile = soundFile.file.read()
+
+    text = pipe(inputFile, batch_size=BATCH_SIZE, generate_kwargs={
+                "task": task}, return_timestamps=True)["text"]
+
+    print("Time took to process the request and return response is {} sec".format(
+        time.time() - start_time))
+    return text

packages.txt

@@ -0,0 +1 @@
+ffmpeg

requirements.txt

@@ -0,0 +1,9 @@
+fastapi
+pydantic
+typing
+transformers
+python-multipart
+torch
+python-multipart
+uvicorn[standard]
+ffmpeg