addons
addons copied to clipboard
home-assistant
Whisper addon increasingly consumes more memory
Describe the issue you are experiencing
After each restarts the RAM consumption is set back to a certain total percentage depending on the language model. This percentage however keeps increasing each time Assist STT is used, and never goes back down, unless the addon is restarted.
What type of installation are you running?
Home Assistant OS
Which operating system are you running on?
Home Assistant Operating System
Which add-on are you reporting an issue with?
Whisper
What is the version of the add-on?
2.6.0
Steps to reproduce the issue
- Start/restart Whisper.
- Trigger Assist voice command.
- Observe RAM usage. Does not reduce, even after a few days.
- Repeat from step 1.
System Health information
System Information
| version | core-2025.6.3 |
|---|---|
| installation_type | Home Assistant OS |
| dev | false |
| hassio | true |
| docker | true |
| user | root |
| virtualenv | false |
| python_version | 3.13.3 |
| os_name | Linux |
| os_version | 6.6.74-haos-raspi |
| arch | aarch64 |
| timezone | Europe/Berlin |
| config_dir | /config |
Home Assistant Cloud
| logged_in | false |
|---|---|
| can_reach_cert_server | ok |
| can_reach_cloud_auth | ok |
| can_reach_cloud | ok |
Home Assistant Supervisor
| host_os | Home Assistant OS 15.2 |
|---|---|
| update_channel | stable |
| supervisor_version | supervisor-2025.06.1 |
| agent_version | 1.7.2 |
| docker_version | 28.0.4 |
| disk_total | 57.8 GB |
| disk_used | 7.5 GB |
| healthy | true |
| supported | true |
| host_connectivity | true |
| supervisor_connectivity | true |
| ntp_synchronized | true |
| virtualization | |
| board | rpi5-64 |
| supervisor_api | ok |
| version_api | ok |
| installed_addons | Matter Server (8.0.0), Mosquitto broker (6.5.1), Tor (6.0.3), motionEye (0.22.1), Piper (1.5.4), Whisper (2.6.0), WireGuard (0.11.0) |
Dashboards
| dashboards | 2 |
|---|---|
| resources | 0 |
| views | 0 |
| mode | storage |
Network Configuration
| adapters | lo (disabled), end0 (enabled, default, auto), hassio (disabled), docker0 (disabled), vethe9e02d5 (disabled), veth7cbe900 (disabled), vethce4d0e8 (disabled), veth62c0ae2 (disabled), veth0612ddb (disabled), vethe68e59a (disabled), veth6f2efc6 (disabled) |
|---|---|
| ipv4_addresses | lo (127.0.0.1/8), end0 (192.168.0.45/24), hassio (172.30.32.1/23), docker0 (172.30.232.1/23), vethe9e02d5 (), veth7cbe900 (), vethce4d0e8 (), veth62c0ae2 (), veth0612ddb (), vethe68e59a (), veth6f2efc6 () |
| ipv6_addresses | lo (::1/128), end0 (2a02:8071:64d1:36a0::e0bd/128, 2a02:8071:64d1:36a0:74ee:8fc8:992:e27f/64, fe80::5a91:21d0:d13e:2584/64), hassio (fe80::84f9:54ff:feae:d5fb/64), docker0 (fe80::646d:14ff:fe89:5588/64), vethe9e02d5 (fe80::14ad:d8ff:fea7:ba3c/64), veth7cbe900 (fe80::f43d:75ff:fe31:88c/64), vethce4d0e8 (fe80::f4ae:6fff:fe30:5c54/64), veth62c0ae2 (fe80::680a:9fff:fecd:9b3a/64), veth0612ddb (fe80::821:f8ff:fe4c:6efb/64), vethe68e59a (fe80::cccf:e6ff:fe6c:8213/64), veth6f2efc6 (fe80::7ca4:b4ff:fece:fa49/64) |
| announce_addresses | 192.168.0.45, 2a02:8071:64d1:36a0::e0bd, 2a02:8071:64d1:36a0:74ee:8fc8:992:e27f, fe80::5a91:21d0:d13e:2584 |
Recorder
| oldest_recorder_run | 13 June 2025 at 05:25 |
|---|---|
| current_recorder_run | 24 June 2025 at 18:51 |
| estimated_db_size | 13.39 MiB |
| database_engine | sqlite |
| database_version | 3.48.0 |
Anything in the Supervisor logs that might be useful for us?
Anything in the add-on logs that might be useful for us?
Additional information
No response
