Skip to content

Commit 3f7be50

Browse files
authored
Merge pull request #85 from intel/update-branch
feat: update speech-to-text service with new server implementation and dependencies (#258)
2 parents eb8e72f + 64036ab commit 3f7be50

File tree

11 files changed

+281
-599
lines changed

11 files changed

+281
-599
lines changed

usecases/ai/digital-avatar/README.md

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -71,6 +71,7 @@ docker compose build
7171

7272
### Start Docker container
7373
```bash
74+
RENDER_GROUP_ID=$(getent group render | cut -d: -f3)
7475
docker compose up -d
7576
```
7677

usecases/ai/digital-avatar/docker-compose.yml

Lines changed: 5 additions & 8 deletions
Original file line numberDiff line numberDiff line change
@@ -104,24 +104,23 @@ services:
104104
build:
105105
context: ../microservices/speech-to-text
106106
dockerfile: Dockerfile
107-
args:
108-
- RENDER_GROUP_ID=110 # Please update this if you are not using Ubuntu 20.04
109107
image: stt_service
110108
hostname: stt_service
111109
container_name: stt_service
112110
privileged: true
111+
group_add:
112+
- ${RENDER_GROUP_ID:-110}
113113
networks:
114114
- app-network
115115
environment:
116-
- STT_MODEL_ID=base
117-
- STT_ENCODED_DEVICE=CPU
118-
- STT_DECODED_DEVICE=CPU
116+
- DEFAULT_MODEL_ID=openai/whisper-tiny
117+
- STT_DEVICE=CPU
119118
- ALLOWED_CORS=["http://localhost"] # frontend url
120119
restart: always
121120
ports:
122121
- 8014:5996
123122
volumes:
124-
- stt_volume:/usr/src/app/data:rw
123+
- ./data:/usr/src/app/data:rw
125124
devices:
126125
- /dev:/dev:rw
127126
- /lib/modules:/lib/modules:rw
@@ -158,10 +157,8 @@ services:
158157
networks:
159158
app-network:
160159

161-
162160
volumes:
163161
tts_volume:
164-
stt_volume:
165162
data_volume:
166163
ollama:
167164
name: "ollama-data"
Lines changed: 41 additions & 33 deletions
Original file line numberDiff line numberDiff line change
@@ -1,43 +1,51 @@
11
# Copyright (C) 2024 Intel Corporation
22
# SPDX-License-Identifier: Apache-2.0
33

4-
FROM openvino/ubuntu22_dev:2024.1.0
4+
FROM openvino/ubuntu22_dev:2024.5.0
55

66
USER root
7-
RUN useradd -m intel
8-
WORKDIR /usr/src/app
9-
RUN apt-get update && apt-get install -y ffmpeg wget
7+
108
# Install dependencies
11-
RUN mkdir neo && \
12-
cd neo && \
13-
wget https://github.com/intel/intel-graphics-compiler/releases/download/igc-1.0.17791.9/intel-igc-core_1.0.17791.9_amd64.deb && \
14-
wget https://github.com/intel/intel-graphics-compiler/releases/download/igc-1.0.17791.9/intel-igc-opencl_1.0.17791.9_amd64.deb && \
15-
wget https://github.com/intel/compute-runtime/releases/download/24.39.31294.12/intel-level-zero-gpu-dbgsym_1.6.31294.12_amd64.ddeb && \
16-
wget https://github.com/intel/compute-runtime/releases/download/24.39.31294.12/intel-level-zero-gpu_1.6.31294.12_amd64.deb && \
17-
wget https://github.com/intel/compute-runtime/releases/download/24.39.31294.12/intel-opencl-icd-dbgsym_24.39.31294.12_amd64.ddeb && \
18-
wget https://github.com/intel/compute-runtime/releases/download/24.39.31294.12/intel-opencl-icd_24.39.31294.12_amd64.deb && \
19-
wget https://github.com/intel/compute-runtime/releases/download/24.39.31294.12/libigdgmm12_22.5.2_amd64.deb && \
20-
dpkg -i *.deb
21-
22-
RUN apt install libtbb12
23-
RUN mkdir npu-driver && \
24-
cd npu-driver && \
25-
wget https://github.com/intel/linux-npu-driver/releases/download/v1.5.1/intel-driver-compiler-npu_1.5.1.20240708-9842236399_ubuntu22.04_amd64.deb && \
26-
wget https://github.com/intel/linux-npu-driver/releases/download/v1.5.1/intel-fw-npu_1.5.1.20240708-9842236399_ubuntu22.04_amd64.deb && \
27-
wget https://github.com/intel/linux-npu-driver/releases/download/v1.5.1/intel-level-zero-npu_1.5.1.20240708-9842236399_ubuntu22.04_amd64.deb && \
28-
dpkg -i *.deb
29-
30-
RUN wget https://github.com/oneapi-src/level-zero/releases/download/v1.17.6/level-zero_1.17.6+u22.04_amd64.deb && \
31-
dpkg -i level-zero*.deb
32-
RUN pip install "transformers>=4.35" "torch>=2.1" onnx "git+https://github.com/huggingface/optimum-intel.git" "peft==0.6.2" --extra-index-url https://download.pytorch.org/whl/cpu
33-
RUN rm -r *.deb neo npu-driver
34-
35-
ARG RENDER_GROUP_ID
36-
RUN groupadd -g ${RENDER_GROUP_ID} render
37-
COPY requirements.txt .
9+
RUN apt-get update && apt-get install -y ffmpeg \
10+
wget \
11+
gnupg2 \
12+
libtbb12 \
13+
python3.11 \
14+
python3.11-venv
15+
16+
# Install GPU drivers
17+
RUN wget -qO - https://repositories.intel.com/gpu/intel-graphics.key | gpg --yes --dearmor --output /usr/share/keyrings/intel-graphics.gpg \
18+
&& echo "deb [arch=amd64,i386 signed-by=/usr/share/keyrings/intel-graphics.gpg] https://repositories.intel.com/gpu/ubuntu jammy client" | tee /etc/apt/sources.list.d/intel-gpu-jammy.list \
19+
&& apt update \
20+
&& apt-get install -y libze1 \
21+
intel-level-zero-gpu \
22+
intel-opencl-icd \
23+
clinfo \
24+
&& rm -rf /var/lib/apt/lists/*
25+
26+
# Install NPU drivers
27+
RUN mkdir /tmp/npu-driver \
28+
&& cd /tmp/npu-driver\
29+
&& wget https://github.com/intel/linux-npu-driver/releases/download/v1.10.0/intel-driver-compiler-npu_1.10.0.20241107-11729849322_ubuntu22.04_amd64.deb \
30+
&& wget https://github.com/intel/linux-npu-driver/releases/download/v1.10.0/intel-fw-npu_1.10.0.20241107-11729849322_ubuntu22.04_amd64.deb \
31+
&& wget https://github.com/intel/linux-npu-driver/releases/download/v1.10.0/intel-level-zero-npu_1.10.0.20241107-11729849322_ubuntu22.04_amd64.deb \
32+
&& wget https://github.com/oneapi-src/level-zero/releases/download/v1.17.6/level-zero_1.17.6+u22.04_amd64.deb \
33+
&& dpkg -i *.deb
34+
35+
RUN mkdir -p /usr/src \
36+
&& chown -R openvino:openvino /usr/src
37+
38+
USER openvino
39+
WORKDIR /usr/src/app
40+
RUN python3 -m venv /usr/src/.venv
41+
ENV PATH="/usr/src/.venv/bin:$PATH"
42+
43+
# Install python dependencies
44+
COPY --chown=openvino:openvino requirements.txt .
3845
RUN python3 -m pip install -r requirements.txt
3946

40-
COPY . .
47+
COPY --chown=openvino:openvino server.py .
48+
COPY --chown=openvino:openvino utils.py .
4149

4250
HEALTHCHECK --interval=60s --timeout=180s --start-period=5s --retries=3 \
43-
CMD wget --no-verbose --no-proxy -O /dev/null --tries=1 http://stt_service:5996/healthcheck || exit 1
51+
CMD wget --no-verbose --no-proxy -O /dev/null --tries=1 http://stt_service:5996/healthcheck || exit 1

usecases/ai/microservices/speech-to-text/main.py

Lines changed: 0 additions & 113 deletions
This file was deleted.
Lines changed: 7 additions & 7 deletions
Original file line numberDiff line numberDiff line change
@@ -1,8 +1,8 @@
1-
fastapi[all]
2-
uvicorn
3-
pydantic<2
4-
openai-whisper==20240927
5-
openvino-dev==2024.1.0
1+
fastapi[all]==0.115.6
2+
uvicorn==0.32.1
3+
64
soundfile==0.12.1
7-
onnx==1.17.0
8-
pydub==0.25.1
5+
pydub==0.25.1
6+
7+
openvino_genai==2024.5.0
8+
optimum-intel[openvino,nncf]==1.21.0

0 commit comments

Comments
 (0)