GPU Speech to text container
Learn about the Speechmatics Transcription GPU container systemPrerequisites
- A license file or a license token
- There is no specific license for the GPU Inference Container, it will run using an existing Speechmatics license for the Real-Time or Batch Container
- Access to our Docker repository
System requirements
The system must have:
- Nvidia GPU(s) with at least 16GB of GPU memory
- Nvidia drivers (see below for supported versions)
- CUDA compute capability of 7.5-9.0 inclusive, which corresponds to the Turing, Ampere, Lovelace, Hopper architectures. Cards with the Volta architecture or below are not able to run the models
- 24 GB RAM
- The nvidia-container-toolkit installed
- Docker version > 19.03
The raw image size of the GPU Inference Container is around 15GB.
Nvidia drivers
The GPU Inference Container is based on CUDA 12.3.2, which requires NVIDIA Driver release 545 or later. If you are running on a data center GPU (e.g, a T4) you can use drivers: 470.57 (or later R470), 525.85 (or later R525), 535.86 (or later R535), or 545.23 (or later R545).
Driver installation can be validated by running nvidia-smi. This command should return the Nvidia driver version and show additional information about the GPU(s).
Cloud instances
The GPU node can be provisioned in the cloud.
Running the image
Currently, each GPU Inference Container can only run on a single GPU.
If a system has more than one GPU, the device must be specified using CUDA_VISIBLE_DEVICES
or selecting the device using the --gpus argument. See Nvidia/CUDA documentation for details.
docker run --rm -it \
-v $PWD/license.json:/license.json \
--gpus '"device=0"' \
-e CUDA_VISIBLE_DEVICES \
-p 8001:8001 \
speechmaticspublic.azurecr.io/sm-gpu-inference-server-en:13.0.0
When the Container starts you should see output similar to this, indicating that the server has started and is ready to serve requests.
I1215 11:43:57.300390 1 server.cc:633]
+----------------------+---------+--------+
| Model | Version | Status |
+----------------------+---------+--------+
| am_en_enhanced | 1 | READY |
| am_en_standard | 1 | READY |
| body_enhanced | 1 | READY |
| body_standard | 1 | READY |
| diar_enhanced | 1 | READY |
| diar_standard | 1 | READY |
| ensemble_en_enhanced | 1 | READY |
| ensemble_en_standard | 1 | READY |
| lm_en_enhanced | 1 | READY |
+----------------------+---------+--------+
...
I1215 11:43:57.375233 1 grpc_server.cc:4819] Started GRPCInferenceService at 0.0.0.0:8001
I1215 11:43:57.375473 1 http_server.cc:3477] Started HTTPService at 0.0.0.0:8000
I1215 11:43:57.417749 1 http_server.cc:184] Started Metrics Service at 0.0.0.0:8002
Batch and Real-time inference
The Inference server can run in two modes: batch, for processing whole files and returning the transcript at the end, and real-time for
processing audio streams. The default mode is batch. To configure the GPU server for real-time, set the environment variable
SM_BATCH_MODE=false by passing it into the docker run command.
The modes correspond to the two types of client speech Container, which are distinguished by their name:
- rt-asr-transcriber-en:<version>
- batch-asr-transcriber-en:<version>
The server can only support one of these modes at once.
Linking to a GPU inference container
Once the GPU Server is running, follow the Instructions for Linking a CPU Container.
Running only one operating point
Operating Points represent different levels of model complexity.
To save GPU memory for throughput, you can run the server with only one Operating Point loaded. To do this, pass the
SM_OPERATING_POINT environment variable to the container and set it to either standard or enhanced.
When running the all language standard Operating Point GPU inference server you must set the SM_OPERATING_POINT environment variable to standard
Monitoring the server
The inference server is based on Nvidia's Triton architecture and as such can be monitored using Triton's inbuilt Prometheus metrics, or the GRPC/HTTP APIs. To expose these, configure an external mapping for port 8002(Prometheus) or 8000(HTTP).
Operating points in GPU inference
When inference is outsourced to a GPU server, alternative GPU-specific models are used, so you should not expect to see identical results compared to CPU-based inference. For convenience, the GPU models are also designated as 'standard' and 'enhanced'.
Docker Compose example
This Docker Compose file will create a Speechmatics GPU Inference Server:
(assumes your license.json file is in the current working directory)
version: "3.8"
networks:
transcriber:
driver: bridge
services:
triton:
image: speechmaticspublic.azurecr.io/sm-gpu-inference-server-en:13.0.0
deploy:
resources:
reservations:
devices:
- driver: nvidia
### Limit to N GPUs
# count: 1
### Pick specific GPUs by device ID
# device_ids:
# - 0
# - 3
capabilities:
- gpu
container_name: triton
networks:
- transcriber
expose:
- 8000/tcp
- 8001/tcp
- 8002/tcp
environment:
- NVIDIA_DRIVER_CAPABILITIES=all
- NVIDIA_VISIBLE_DEVICES=all
- CUDA_VISIBLE_DEVICES=0
volumes:
- $PWD/license.json:/license.json:ro
GPU Inference Performance
This is a comparison of the performance and estimated running costs of transcription executing on standard Azure VMs.
Benchmark metrics
The benchmark uses the following configuration:
For GPU Operating Points, Transcribers and Inference Server were all run on a single VM node.
Footnotes
-
Throughput is measured as hours of audio per hour of runtime. A throughput of 50 would mean that in one hour, the system as a whole can transcribe 50 hours of audio. ↩
-
An RTF of 1 would mean that a one hour file would take one hour to transcribe. An RTF of 0.1 would mean that a one hour file would take six minutes to transcribe. Benchmark RTFs are representative for processing audio files over 20 minutes in duration using
parallel=4. ↩