chore(model gallery): add voxcpm, whisperx, moonshine-tiny

gallery/index.yaml

@@ -52,6 +52,66 @@
     - filename: voxtral-model/tekken.json
       uri: https://huggingface.co/mistralai/Voxtral-Mini-4B-Realtime-2602/resolve/main/tekken.json
       sha256: 8434af1d39eba99f0ef46cf1450bf1a63fa941a26933a1ef5dbbf4adf0d00e44
+- name: moonshine-tiny
+  license: apache-2.0
+  url: "github:mudler/LocalAI/gallery/virtual.yaml@master"
+  description: |
+    Moonshine Tiny is a lightweight speech-to-text model optimized for fast transcription. It is designed for efficient on-device ASR with high accuracy relative to its size.
+  urls:
+    - https://github.com/moonshine-ai/moonshine
+  tags:
+    - stt
+    - speech-to-text
+    - asr
+    - audio-transcription
+    - cpu
+    - gpu
+  overrides:
+    backend: moonshine
+    known_usecases:
+      - transcript
+    parameters:
+      model: moonshine/tiny
+- name: whisperx-tiny
+  license: mit
+  url: "github:mudler/LocalAI/gallery/virtual.yaml@master"
+  description: |
+    WhisperX Tiny is a fast and accurate speech recognition model with speaker diarization capabilities. Built on OpenAI's Whisper with additional features for alignment and speaker segmentation.
+  urls:
+    - https://github.com/m-bain/whisperX
+  tags:
+    - stt
+    - speech-to-text
+    - asr
+    - audio-transcription
+    - speaker-diarization
+    - cpu
+    - gpu
+  overrides:
+    backend: whisperx
+    known_usecases:
+      - transcript
+    parameters:
+      model: tiny
+- name: voxcpm-1.5
+  license: apache-2.0
+  url: "github:mudler/LocalAI/gallery/virtual.yaml@master"
+  description: |
+    VoxCPM 1.5 is an end-to-end text-to-speech (TTS) model from ModelBest. It features zero-shot voice cloning and high-quality speech synthesis capabilities.
+  urls:
+    - https://huggingface.co/openbmb/VoxCPM1.5
+  tags:
+    - tts
+    - text-to-speech
+    - voice-cloning
+    - cpu
+    - gpu
+  overrides:
+    backend: voxcpm
+    known_usecases:
+      - tts
+    parameters:
+      model: openbmb/VoxCPM1.5
 - name: "ace-step-turbo"
   license: mit
   tags:
@@ -84,7 +144,7 @@
       - "offload_to_cpu:false"
       - "offload_dit_to_cpu:false"
       - "init_lm:true"
       - "lm_model_path:acestep-5Hz-lm-0.6B" # or acestep-5Hz-lm-4B
       - "lm_backend:pt"
       - "temperature:0.85"
       - "top_p:0.9"
@@ -317,7 +377,7 @@
     known_usecases:
       - tts
     tts:
       voice: Aiden # Available speakers: Vivian, Serena, Uncle_Fu, Dylan, Eric, Ryan, Aiden, Ono_Anna, Sohee
     parameters:
       model: Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice
 - !!merge <<: *qwen-tts
@@ -329,7 +389,7 @@
     known_usecases:
       - tts
     tts:
       voice: Aiden # Available speakers: Vivian, Serena, Uncle_Fu, Dylan, Eric, Ryan, Aiden, Ono_Anna, Sohee
     parameters:
       model: Qwen/Qwen3-TTS-12Hz-0.6B-CustomVoice
 - &qwen-asr
@@ -4370,7 +4430,7 @@
     - gemma3
     - gemma-3
   overrides:
     #mmproj: gemma-3-27b-it-mmproj-f16.gguf
     parameters:
       model: gemma-3-27b-it-Q4_K_M.gguf
   files:
@@ -4388,7 +4448,7 @@
   description: |
     google/gemma-3-12b-it is an open-source, state-of-the-art, lightweight, multimodal model built from the same research and technology used to create the Gemini models. It is capable of handling text and image input and generating text output. It has a large context window of 128K tokens and supports over 140 languages. The 12B variant has been fine-tuned using the instruction-tuning approach. Gemma 3 models are suitable for a variety of text generation and image understanding tasks, including question answering, summarization, and reasoning. Their relatively small size makes them deployable in environments with limited resources such as laptops, desktops, or your own cloud infrastructure.
   overrides:
     #mmproj: gemma-3-12b-it-mmproj-f16.gguf
     parameters:
       model: gemma-3-12b-it-Q4_K_M.gguf
   files:
@@ -4406,7 +4466,7 @@
   description: |
     Gemma is a family of lightweight, state-of-the-art open models from Google, built from the same research and technology used to create the Gemini models. Gemma 3 models are multimodal, handling text and image input and generating text output, with open weights for both pre-trained variants and instruction-tuned variants. Gemma 3 has a large, 128K context window, multilingual support in over 140 languages, and is available in more sizes than previous versions. Gemma 3 models are well-suited for a variety of text generation and image understanding tasks, including question answering, summarization, and reasoning. Their relatively small size makes it possible to deploy them in environments with limited resources such as laptops, desktops or your own cloud infrastructure, democratizing access to state of the art AI models and helping foster innovation for everyone. Gemma-3-4b-it is a 4 billion parameter model.
   overrides:
     #mmproj: gemma-3-4b-it-mmproj-f16.gguf
     parameters:
       model: gemma-3-4b-it-Q4_K_M.gguf
   files:
@@ -7624,7 +7684,7 @@
       sha256: 2756551de7d8ff7093c2c5eec1cd00f1868bc128433af53f5a8d434091d4eb5a
       uri: huggingface://Triangle104/Nano_Imp_1B-Q8_0-GGUF/nano_imp_1b-q8_0.gguf
 - &smollm
   url: "github:mudler/LocalAI/gallery/chatml.yaml@master" ## SmolLM
   name: "smollm-1.7b-instruct"
   icon: https://huggingface.co/datasets/HuggingFaceTB/images/resolve/main/banner_smol.png
   tags:
@@ -7668,7 +7728,7 @@
       sha256: decd2598bc2c8ed08c19adc3c8fdd461ee19ed5708679d1c54ef54a5a30d4f33
       uri: huggingface://HuggingFaceTB/SmolLM2-1.7B-Instruct-GGUF/smollm2-1.7b-instruct-q4_k_m.gguf
 - &llama31
   url: "github:mudler/LocalAI/gallery/llama3.1-instruct.yaml@master" ## LLama3.1
   icon: https://avatars.githubusercontent.com/u/153379578
   name: "meta-llama-3.1-8b-instruct"
   license: llama3.1