add speech to text model

charts/kubeai/Chart.yaml

@@ -31,7 +31,7 @@ dependencies:
   # These are instances of the Model custom resource.
   - name: models
     condition: models.enabled
-    version: 0.1.0
+    version: 0.1.1
 
 
 keywords: ["LLM", "AI"]

charts/kubeai/charts/models/Chart.yaml

@@ -15,7 +15,7 @@ type: application
 # This is the chart version. This version number should be incremented each time you make changes
 # to the chart and its templates, including the app version.
 # Versions are expected to follow Semantic Versioning (https://semver.org/)
-version: 0.1.0
+version: 0.1.1
 
 # This is the version number of the application being deployed. This version number should be
 # incremented each time you make changes to the application. Versions are not expected to

charts/kubeai/charts/models/values.yaml

@@ -76,4 +76,11 @@ catalog:
     url: "ollama://qwen2:0.5b"
     engine: OLlama
     resourceProfile: cpu:1
+  faster-whisper-medium-en-cpu:
+    enabled: false
+    features: ["SpeechToText"]
+    owner: Systran
+    url: "hf://Systran/faster-whisper-medium.en"
+    engine: FasterWhisper
+    resourceProfile: cpu:1
 

test/quickstart.sh

@@ -63,6 +63,8 @@ models:
       enabled: true
     nomic-embed-text-cpu:
       enabled: true
+    faster-whisper-medium-en-cpu:
+      enabled: true
 EOF
 
 wait_for_pod_ready model=gemma2-2b-cpu
@@ -73,3 +75,14 @@ curl http://localhost:8000/openai/v1/completions \
   -H "Content-Type: application/json" \
   -d '{"model": "gemma2-2b-cpu", "prompt": "Who was the first president of the United States?", "max_tokens": 40}'
 
+# Test the speech to text endpoint
+curl -L -o kubeai.mp4 https://github.com/user-attachments/assets/711d1279-6af9-4c6c-a052-e59e7730b757
+result=$(curl http://localhost:8000/openai/v1/audio/transcriptions \
+  -F "file=@kubeai.mp4" \
+  -F "language=en" | jq '.text | ascii_downcase | contains("kubernetes")')
+if [ "$result" = "true" ]; then
+  echo "The transcript contains 'kubernetes'."
+else
+  echo "The text does not contain 'kubernetes'."
+  exit 1
+fi