Merge pull request #58 from linuxserver/gpu-legacy-autolang

Author: thespad

README.md

@@ -94,10 +94,11 @@ services:
       - PUID=1000
       - PGID=1000
       - TZ=Etc/UTC
-      - WHISPER_MODEL=tiny-int8
+      - DEBUG= #optional
       - LOCAL_ONLY= #optional
       - WHISPER_BEAM=1 #optional
-      - WHISPER_LANG=en #optional
+      - WHISPER_LANG=auto #optional
+      - WHISPER_MODEL=auto #optional
     volumes:
       - /path/to/faster-whisper/data:/config
     ports:
@@ -113,10 +114,11 @@ docker run -d \
   -e PUID=1000 \
   -e PGID=1000 \
   -e TZ=Etc/UTC \
-  -e WHISPER_MODEL=tiny-int8 \
+  -e DEBUG= `#optional` \
   -e LOCAL_ONLY= `#optional` \
   -e WHISPER_BEAM=1 `#optional` \
-  -e WHISPER_LANG=en `#optional` \
+  -e WHISPER_LANG=auto `#optional` \
+  -e WHISPER_MODEL=auto `#optional` \
   -p 10300:10300 \
   -v /path/to/faster-whisper/data:/config \
   --restart unless-stopped \
@@ -133,10 +135,11 @@ Containers are configured using parameters passed at runtime (such as those abov
 | `-e PUID=1000` | for UserID - see below for explanation |
 | `-e PGID=1000` | for GroupID - see below for explanation |
 | `-e TZ=Etc/UTC` | specify a timezone to use, see this [list](https://en.wikipedia.org/wiki/List_of_tz_database_time_zones#List). |
-| `-e WHISPER_MODEL=tiny-int8` | Whisper model that will be used for transcription. From `tiny`, `base`, `small` and `medium`, all with `-int8` compressed variants |
+| `-e DEBUG=` | If set to `true`, or any other value, the container will output debug logs. |
 | `-e LOCAL_ONLY=` | If set to `true`, or any other value, the container will not attempt to download models from HuggingFace and will only use locally-provided models. |
 | `-e WHISPER_BEAM=1` | Number of candidates to consider simultaneously during transcription. |
-| `-e WHISPER_LANG=en` | Language that you will speak to the add-on. |
+| `-e WHISPER_LANG=auto` | Two character code for the language that you will speak to the add-on. |
+| `-e WHISPER_MODEL=auto` | Whisper model that will be used for transcription. From [here](https://github.com/SYSTRAN/faster-whisper/blob/master/faster_whisper/utils.py#L11-L31). |
 | `-v /config` | Local path for Whisper config files. |
 | `--read-only=true` | Run container with a read-only filesystem. Please [read the docs](https://docs.linuxserver.io/misc/read-only/). |
 
@@ -302,6 +305,7 @@ Once registered you can define the dockerfile to use with `-f Dockerfile.aarch64
 
 ## Versions
 
+* **26.01.26:** - Default to `auto` for model and language if not set.
 * **20.08.25:** - Add gpu-legacy branch for pre-Turing cards.
 * **10.08.25:** - Add support for local-only mode.
 * **05.12.24:** - Build from Github releases rather than Pypi.

readme-vars.yml

@@ -18,9 +18,7 @@ development_versions_items:
 # container parameters
 common_param_env_vars_enabled: true
 param_container_name: "{{ project_name }}"
-param_usage_include_env: true
-param_env_vars:
-  - {env_var: "WHISPER_MODEL", env_value: "tiny-int8", desc: "Whisper model that will be used for transcription. From `tiny`, `base`, `small` and `medium`, all with `-int8` compressed variants", env_options: ["tiny-int8", "tiny", "base-int8", "base", "small-int8", "small", "medium-int8"]}
+param_usage_include_env: false
 param_usage_include_vols: true
 param_volumes:
   - {vol_path: "/config", vol_host_path: "/path/to/{{ project_name }}/data", desc: "Local path for Whisper config files."}
@@ -30,9 +28,11 @@ param_ports:
 # optional container parameters
 opt_param_usage_include_env: true
 opt_param_env_vars:
+  - {env_var: "DEBUG", env_value: "", desc: "If set to `true`, or any other value, the container will output debug logs."}
   - {env_var: "LOCAL_ONLY", env_value: "", desc: "If set to `true`, or any other value, the container will not attempt to download models from HuggingFace and will only use locally-provided models."}
   - {env_var: "WHISPER_BEAM", env_value: "1", desc: "Number of candidates to consider simultaneously during transcription."}
-  - {env_var: "WHISPER_LANG", env_value: "en", desc: "Language that you will speak to the add-on."}
+  - {env_var: "WHISPER_LANG", env_value: "auto", desc: "Two character code for the language that you will speak to the add-on."}
+  - {env_var: "WHISPER_MODEL", env_value: "auto", desc: "Whisper model that will be used for transcription. From [here](https://github.com/SYSTRAN/faster-whisper/blob/master/faster_whisper/utils.py#L11-L31)."}
 readonly_supported: true
 # application setup block
 app_setup_block_enabled: true
@@ -85,6 +85,7 @@ init_diagram: |
   "faster-whisper:gpu-legacy" <- Base Images
 # changelog
 changelogs:
+  - {date: "26.01.26:", desc: "Default to `auto` for model and language if not set."}
   - {date: "20.08.25:", desc: "Add gpu-legacy branch for pre-Turing cards."}
   - {date: "10.08.25:", desc: "Add support for local-only mode."}
   - {date: "05.12.24:", desc: "Build from Github releases rather than Pypi."}

root/etc/s6-overlay/s6-rc.d/svc-whisper/run

@@ -8,9 +8,10 @@ exec \
         s6-setuidgid abc python3 -m wyoming_faster_whisper \
         --uri 'tcp://0.0.0.0:10300' \
         --device cuda \
-        --model "${WHISPER_MODEL}" \
+        --model "${WHISPER_MODEL:-auto}" \
         --beam-size "${WHISPER_BEAM:-1}" \
-        --language "${WHISPER_LANG:-en}" \
+        --language "${WHISPER_LANG:-auto}" \
         --data-dir /config \
         --download-dir /config \
+        ${DEBUG:+--debug} \
         ${LOCAL_ONLY:+--local-files-only}