Open-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving.
Python asraudiochineseemotion-recognitionfunasrmcp-servermultilingual-asropenai-compatible-apiparaformerpunctuationpytorchreal-time-asrspeaker-diarizationspeech-recognitionspeech-to-textstreaming-asrtranscriptionvllmvoice-activity-detectionwhisper-alternative
apiVersion: v1
kind: PersistentVolumeClaim
metadata:
name: funasr-moss-cache
spec:
accessModes:
- ReadWriteOnce
resources:
requests:
storage: 40Gi
---
apiVersion: apps/v1
kind: Deployment
metadata:
name: funasr-moss-api
spec:
replicas: 1
strategy:
type: Recreate
selector:
matchLabels:
app.kubernetes.io/name: funasr-moss-api
template:
metadata:
labels:
app.kubernetes.io/name: funasr-moss-api
spec:
containers:
- name: api
image: funasr-moss-api:local
imagePullPolicy: IfNotPresent
env:
- name: FUNASR_MODEL
value: moss-transcribe-diarize
- name: FUNASR_DEVICE
value: cuda:0
- name: FUNASR_PORT
value: "8000"
ports:
- name: http
containerPort: 8000
startupProbe:
httpGet:
path: /health
port: http
periodSeconds: 10
timeoutSeconds: 5
failureThreshold: 60
readinessProbe:
httpGet:
path: /health
port: http
periodSeconds: 10
resources:
requests:
cpu: "4"
memory: 24Gi
nvidia.com/gpu: "1"
limits:
memory: 48Gi
nvidia.com/gpu: "1"
volumeMounts:
- name: cache
mountPath: /root/.cache
- name: dshm
mountPath: /dev/shm
volumes:
- name: cache
persistentVolumeClaim:
claimName: funasr-moss-cache
- name: dshm
emptyDir:
medium: Memory
sizeLimit: 8Gi
---
apiVersion: v1
kind: Service
metadata:
name: funasr-moss-api
spec:
selector:
app.kubernetes.io/name: funasr-moss-api
ports:
- name: http
port: 8000
targetPort: http