SpeechSquad¶

Local Deployment¶

This SpeechSquad sample application can be deployed locally. No load balancing is required. ASR, NLP, and TTS Jarvis services are required to be running.

Installation¶

Install and start Jarvis locally (see Local (Docker)).
Install the SpeechSquad Server:

docker pull nvcr.io/nvidia/speech_squad:1.0.0-b.1

Download the dataset:

wget https://github.com/NVIDIA/speechsquad/releases/download/v1.0.0-b.1/speechsquad_sample_public_v1.tgz
tar xzf speechsquad_sample_public_v1.tgz

Running the Test Locally¶

Start the Jarvis Speech Server (if you have not already):
```
bash jarvis_start.sh
```

Start the SpeechSquad Server:

docker run -it --net=host \
    nvcr.io/nvidia/speech_squad:1.0.0-b.1 \
    speechsquad_server  \
        -tts_service_url=0.0.0.0:50051 \
        -nlp_service_url=0.0.0.0:50051 \
        -asr_service_url=0.0.0.0:50051

Run a performance test:

docker run -it --net=host \
    -v $(pwd)/speechsquad_sample_public_v1:/work/test_files/speech_squad/ \
    nvcr.io/nvidia/speech_squad:1.0.0-b.1 \
    speechsquad_perf_client \
        --squad_questions_json=/work/test_files/speech_squad/recorded_questions.jl \
        --squad_dataset_json=/work/test_files/speech_squad/manifest.json \
        --speech_squad_uri=0.0.0.0:1337 \
        --chunk_duration_ms=800 \
        --executor_count=1 \
        --num_iterations=1 \
        --num_parallel_requests=64 \
        --print_results=false

Cloud Deployment¶

This SpeechSquad sample application requires a fully setup Jarvis environment with working L7 load balancing and name resolution. To best validate scaling, we recommend a distinct installation for each service type. To do this, three different invocations of Helm install are needed. This requires a minimum of 3 GPU’s on the intended system. In order to scale up each service, many more GPU’s are needed.

SpeechSquad may also be run against a Jarvis speech system with all three services running on a single GPU, but do not expect optimal performance.

Assuming values.yaml has been updated for all other configuration details:

To setup an NLP only service, run:

helm install nlp-jarvis-api jarvis-api \
    --jarvis.speechServices.asr=false \
    --jarvis.speechServices.tts=false

To setup an ASR only service, run:

helm install asr-jarvis-api jarvis-api \
    --jarvis.speechServices.nlp=false \
    --jarvis.speechServices.tts=false

To setup a TTS only service, run:

helm install tts-jarvis-api jarvis-api \
    --jarvis.speechServices.asr=false \
    --jarvis.speechServices.nlp=false``

Then, each deployment can be scaled independently using kubectl scale per normal.

Installation¶

At a minimum, the SpeechSquad Server container (sss) expects to be able to route to the Jarvis Speech container. For any sort of testing at scale, the name resolution needs to be functioning due to the use of Layer 7 load balancers. Many issues can be resolved by validating container routing first, then name resolution between pods.

Conceptually, a successful SpeechSquad deployment will have one or more of each pod type. Each pod needs proper connectivity (routing and optionally name resolution) to the pods around it.

+---------------+     +----------------+     +---------------+
|               |     |                |     |               |
| Jarvis Speech | --- | SpeechSquad    | --- |  SpeechSquad  |
|               |     |    Server      |     |     Client    |
+---------------+     +----------------+     +---------------+

Ensuring that each pod is running correctly before moving on to the next, to ease troubleshooting, ensure:

Jarvis is running and responding to client queries before SpeechSquad is installed.

SpeechSquad server comes up and connects to Jarvis (either using IP:PORT or FQDN:PORT).

SpeechSquad client connects to sss (either using appropriate IP:PORT or FQDN:PORT).

Fetch the Helm chart that is hosted on NGC. Ensure you add authentication options, if needed.
```
helm fetch https://helm.ngc.nvidia.com/nvidia/charts/speechsquad-1.0.0-b.1.tgz
```
Alternatively, the git repository can be pulled from github.com/nvidia/speechsquad.
Update the values.yaml to match the fully qualified domain names (fqdn)’s for this installation, if using name resolution. SpeechSquad should also have a fqdn for its server (for example, speechsquad.jarvis.nvda). The SpeechSquad server expects endpoints for each TTS, NLP, and ASR service. For example, by default, the values.yaml containts the following:
- nlp_uri: "jarvis.nvda"
- asr_uri: "jarvis.nvda"
- tts_uri: "jarvis.nvda"

If SpeechSquad is being deployed on a single system, these URI’s can be repalced with the IP address.

For load balancing, it is required that the SpeechSquad server container can resolve jarvis.nvda to the endpoint exposing jarvis-speech. The chart allows for /etc/hosts in the container to be set at launch time by setting the .Values.sss.lb_ip: value to match what jarvis.nvda should resolve too.

In the following example, we see that the external-ip of the load balancer is 10.42.0.190. Since we want load balancing, set the .Values.sss.lb_ip in the values.yaml for SpeechSquad to match this ip.

$ kubectl get services
NAME           TYPE           CLUSTER-IP       EXTERNAL-IP   PORT(S)                                                        AGE
jarvis-api     LoadBalancer   10.97.16.15      10.42.0.191   8000:31308/TCP,8001:30646/TCP,8002:30042/TCP,50051:32669/TCP   3d19h
kubernetes     ClusterIP      10.96.0.1        <none>        443/TCP                                                        50d
traefik        LoadBalancer   10.107.200.114   10.42.0.190   80:32131/TCP,443:31802/TCP

After the values.yaml reflects the environment correctly, install the Helm chart and optionally pass any command-line options for further customization.

helm install speechsquad speechsquad

This should provide two pods in the cluster, one for the server (SSS) and the other for the clnt.

$ kubectl get pods

NAME                           READY   STATUS    RESTARTS   AGE
clnt-ss-5945877dc7-wk9fs       1/1     Running   0          5d16h
jarvis-api-6947945c67-4f7gt    1/1     Running   0          7d12h
speechsquad-6974455879-spxgt   1/1     Running   0          5d13h

Validate that you have ingressroutes setup correctly.

$ kubectl get ingressroute
NAME                        AGE
jarvis-ingressroute         7d12h
speech-squad-ingressroute   5d16h
traefik-dashboard           23d

Issue describe to ensure the correct Host() clause appears. Entry Points is what port the load balancer will accept traffic from. Here we use web which is port 80; the services section will forward traffic that matches the host clause to said service on the port using the specificed protocol.

If using name resolution, kubectl describe ingressroute to ensure the correct Host() clause appears. Entry Points is what port the load balancer will accept traffic from. Here, we use web which is port 80; the services section will forward traffic that matches the host clause to said service on the port using the specificed protocol.

$ kubectl describe ingressroute jarvis-ingressroute
...
    web
Routes:
  Kind:   Rule
  Match:  Host(`jarvis.nvda`)
  Services:
    Name:    jarvis-api
    Port:    50051
    Scheme:  h2c

and

$ kubectl describe ingressroute speech-squad-ingressroute

  Entry Points:
  web
Routes:
  Kind:   Rule
  Match:  Host(`speechsquad.jarvis.nvda`, `speechsquad.jarvis.nvda.nvidia.com`)
  Services:
    Name:    speech-squad
    Port:    1337
    Scheme:  h2c

Services can also be validated for each ingressroute by pulling the service name from the route and checking its existance.

..prompt
```
kubectl get service `kubectl get ingressroute speech-squad-ingressroute -o=json | jq .spec.routes[0].services[0].name -r`
```

Containers¶

Pull the container with the command below:

docker pull nvcr.io/|NgcOrgTeam|/speech_squad:1.0.0-b.1

Dataset¶

We provide a toy dataset with five examples that can be iterated over an arbitrary number of times for generating load. The data accompanies the official SpeechSquad GitHub Release.

Running the Test¶

You can run the client from a Docker container or by kubectl exec into the node in the cluster.

To execute the client, ensure the dataset above is in your current working directory.

ls
build    client           CREDITS.md  speechsquad_sample_public_v1      LICENSE    reference
CLA.pdf  CONTRIBUTING.md  Dockerfile  speechsquad_sample_public_v1.tgz  README.md  server

Run the following command to perform the test from the same directory.

docker run -it --net=host -v $(pwd):/work/test_files/speech_squad/ nvcr.io/nvidia/speech_squad:1.0.0-b.1 \
    speechsquad_perf_client \
      --squad_questions_json=/work/test_files/speech_squad/speechsquad_sample_public_v1/recorded_questions.jl \
      --squad_dataset_json=/work/test_files/speech_squad/speechsquad_sample_public_v1/manifest.json \
      --speech_squad_uri=speechsquad.jarvis.nvda:80 \
      --chunk_duration_ms=800 --executor_count=1 \
      --num_iterations=1 --num_parallel_requests=64 \
      --print_results=false

If using kubectl exec, the client node must have access to the data volume with the speechsquad_sample_public_v1 in it. This is currently hardcoded to /sss_data, so that the speechsquad_sample_public_v1 directory needs to live in /sss_data on the Kubernetes host which is also running the client container pod. This is controlled in the deployment.yaml file under Volumes and VolumeMounts.

export CLNT_POD=$(kubectl get pods | grep clnt  | awk '{print $1}')
kubectl exec --stdin --tty $CLNT_POD -- /bin/bash
speechsquad_perf_client \
   --squad_questions_json=/work/test_files/speech_squad/speechsquad_sample_public_v1/recorded_questions.jl \
   --squad_dataset_json=/work/test_files/speech_squad/speechsquad_sample_public_v1/manifest.json \
   --speech_squad_uri=speechsquad.jarvis.nvda:80 \
   --chunk_duration_ms=800 --executor_count=1 \
   --num_iterations=1 --num_parallel_requests=64 --print_results=false