speecht5: Support air gapped environment

helm-charts/common/speecht5/README.md

@@ -11,6 +11,35 @@ export MODELDIR=/mnt/opea-models
 helm install speecht5 speecht5 --set global.modelUseHostPath=${MODELDIR}
 ```
 
+### Install the microservice in air gapped (offline) mode
+
+To run `speecht5` microservice in an air gapped environment, users are required to pre-download the models `microsoft/speecht5_tts` and `microsoft/speecht5_hifigan` to a shared storage.
+
+Below is an example for using node level local directory to download the model data:
+
+Assuming the model data is shared using node-local directory `/mnt/opea-models`.
+
+```
+# On every K8s node, run the following command:
+export MODEL_DIR=/mnt/opea-models
+# Download model, assumes Python huggingface_hub[cli] module is already installed
+huggingface-cli download --cache-dir "${MODEL_DIR}" microsoft/speecht5_tts
+huggingface-cli download --cache-dir "${MODEL_DIR}" microsoft/speecht5_hifigan
+# On K8s master node, run the following command:
+# Install using Helm with the following additional parameters:
+helm install ... ... --set global.offline=true,global.modelUseHostPath=${MODEL_DIR}
+```
+
+Assuming we share the offline data on cluster level using a persistent volume (PV), first we need to create the persistent volume claim (PVC) with name `opea-model-pvc` to store the model data.
+
+```
+# Download model openai/whisper-small at the root directory of the corresponding PV
+# ... ...
+# Install using Helm with the following additional parameters:
+# export MODEL_PVC=opea-model-pvc
+# helm install ... ... --set global.offline=true,global.modelUsePVC=${MODEL_PVC}
+```
+
 ## Verify
 
 Use port-forward to access it from localhost.

helm-charts/common/speecht5/templates/configmap.yaml

@@ -18,4 +18,7 @@ data:
   HF_ENDPOINT: {{ .Values.global.HF_ENDPOINT | quote}}
   {{- end }}
   HUGGINGFACE_HUB_CACHE: "/data"
-  HF_TOKEN: {{ .Values.global.HUGGINGFACEHUB_API_TOKEN | default .Values.global.HF_TOKEN | quote }}
+  HF_TOKEN: {{ .Values.global.HUGGINGFACEHUB_API_TOKEN | quote}}
+  {{- if .Values.global.offline }}
+  HF_HUB_OFFLINE: "1"
+  {{- end }}

helm-charts/common/speecht5/templates/deployment.yaml

@@ -28,7 +28,7 @@ spec:
       serviceAccountName: {{ include "speecht5.serviceAccountName" . }}
       securityContext:
         {{- toYaml .Values.podSecurityContext | nindent 8 }}
-      {{- if not (hasPrefix "/data/" .Values.TTS_MODEL_PATH) }}
+      {{- if and (not .Values.global.offline) (not (hasPrefix "/data/" .Values.TTS_MODEL_PATH)) }}
       initContainers:
         - name: model-downloader
           envFrom:
@@ -118,8 +118,10 @@ spec:
           hostPath:
             path: {{ .Values.global.modelUseHostPath }}
             type: Directory
-          {{- else }}
+          {{- else if not .Values.global.offline }}
           emptyDir: {}
+          {{- else }}
+          {{- fail "'global.modelUsePVC' or 'global.modelUseHostPath' must be set in offline mode" }}
           {{- end }}
         - name: tmp
           emptyDir: {}

helm-charts/common/speecht5/values.yaml

@@ -94,6 +94,9 @@ global:
   # If set, and serviceAccount.create is false, it will assume this service account is already created by others.
   sharedSAName: ""
 
+  # Running microservice in air gapped (offline) mode
+  # If offline is enabled, user must set either modelUseHostPath or modelUsePVC and download models `microsoft/speecht5_tts` and `microsoft/speecht5_hifigan`.
+  offline: false
   # Choose where to save your downloaded models
   # Set modelUseHostPath for local directory, this is good for one node test. Example:
   # modelUseHostPath: /mnt/opea-models