Instructions to use aaronpham/speakilo-cpu-models with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use aaronpham/speakilo-cpu-models with llama.cpp:
Install (macOS, Linux)
curl -LsSf https://llama.app/install.sh | sh # Start a local OpenAI-compatible server with a web UI: llama serve -hf aaronpham/speakilo-cpu-models:Q4_0 # Run inference directly in the terminal: llama cli -hf aaronpham/speakilo-cpu-models:Q4_0
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf aaronpham/speakilo-cpu-models:Q4_0 # Run inference directly in the terminal: llama cli -hf aaronpham/speakilo-cpu-models:Q4_0
Build from source code
git clone https://github.com/ggml-org/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-app # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama serve -hf aaronpham/speakilo-cpu-models:Q4_0 # Run inference directly in the terminal: ./build/bin/llama cli -hf aaronpham/speakilo-cpu-models:Q4_0
Use Docker
docker model run hf.co/aaronpham/speakilo-cpu-models:Q4_0
- Llama new
- LM Studio
- Jan
- Ollama
How to use aaronpham/speakilo-cpu-models with Ollama:
ollama run hf.co/aaronpham/speakilo-cpu-models:Q4_0
- Unsloth Desktop
- Docker Model Runner
How to use aaronpham/speakilo-cpu-models with Docker Model Runner:
docker model run hf.co/aaronpham/speakilo-cpu-models:Q4_0
- Lemonade
How to use aaronpham/speakilo-cpu-models with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull aaronpham/speakilo-cpu-models:Q4_0
Run and chat with the model
lemonade run user.speakilo-cpu-models-Q4_0
List all available models
lemonade list
- Atomic Chat
Add ASR and MT checksums
Browse files- checksums.json +47 -3
checksums.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
{
|
| 2 |
"repo_id": "aaronpham/speakilo-cpu-models",
|
| 3 |
"visibility": "private",
|
| 4 |
-
"scope": "CPU VAD, LID,
|
| 5 |
"files": {
|
| 6 |
"vad/silero/silero_vad_v6.onnx": {
|
| 7 |
"bytes": 1245151,
|
|
@@ -6674,8 +6674,52 @@
|
|
| 6674 |
"sha256": "3c4cc3b9fd5b07a6c20d04b0e379ecb0d0d3304024e949967992905800a0d818",
|
| 6675 |
"source_group": "tts/ppaso_ko",
|
| 6676 |
"relative_path": "runtime/dict/korean_mfa.dict"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6677 |
}
|
| 6678 |
},
|
| 6679 |
-
"total_bytes":
|
| 6680 |
-
"file_count":
|
| 6681 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"repo_id": "aaronpham/speakilo-cpu-models",
|
| 3 |
"visibility": "private",
|
| 4 |
+
"scope": "CPU VAD, LID, ASR, TTS assets plus the selected Hy-MT2 GGUF",
|
| 5 |
"files": {
|
| 6 |
"vad/silero/silero_vad_v6.onnx": {
|
| 7 |
"bytes": 1245151,
|
|
|
|
| 6674 |
"sha256": "3c4cc3b9fd5b07a6c20d04b0e379ecb0d0d3304024e949967992905800a0d818",
|
| 6675 |
"source_group": "tts/ppaso_ko",
|
| 6676 |
"relative_path": "runtime/dict/korean_mfa.dict"
|
| 6677 |
+
},
|
| 6678 |
+
"asr/gipformer/decoder.int8.onnx": {
|
| 6679 |
+
"bytes": 1308690,
|
| 6680 |
+
"sha256": "e0a156b5454722a524230f9e35d5d928cfcdd3723437b418e5bd5e04f1c3a101",
|
| 6681 |
+
"source_group": "asr/gipformer",
|
| 6682 |
+
"relative_path": "decoder.int8.onnx"
|
| 6683 |
+
},
|
| 6684 |
+
"asr/gipformer/encoder.int8.onnx": {
|
| 6685 |
+
"bytes": 70876359,
|
| 6686 |
+
"sha256": "b528768939c7711a889be81a718ea7f2ee50d0d2d384d53f399e15b44bd9408c",
|
| 6687 |
+
"source_group": "asr/gipformer",
|
| 6688 |
+
"relative_path": "encoder.int8.onnx"
|
| 6689 |
+
},
|
| 6690 |
+
"asr/gipformer/joiner.int8.onnx": {
|
| 6691 |
+
"bytes": 1033417,
|
| 6692 |
+
"sha256": "12636559d135315f002a1e1b477077d415e888477378db0fd450aee5b21ac551",
|
| 6693 |
+
"source_group": "asr/gipformer",
|
| 6694 |
+
"relative_path": "joiner.int8.onnx"
|
| 6695 |
+
},
|
| 6696 |
+
"asr/gipformer/tokens.txt": {
|
| 6697 |
+
"bytes": 25847,
|
| 6698 |
+
"sha256": "f536d03c2e95ebd2930cf0abec88e823bd17d3c1933da7ae6a82db3b80605e15",
|
| 6699 |
+
"source_group": "asr/gipformer",
|
| 6700 |
+
"relative_path": "tokens.txt"
|
| 6701 |
+
},
|
| 6702 |
+
"asr/sensevoice-sherpa-int8/model.int8.onnx": {
|
| 6703 |
+
"bytes": 239233841,
|
| 6704 |
+
"sha256": "c71f0ce00bec95b07744e116345e33d8cbbe08cef896382cf907bf4b51a2cd51",
|
| 6705 |
+
"source_group": "asr/sensevoice-sherpa-int8",
|
| 6706 |
+
"relative_path": "model.int8.onnx"
|
| 6707 |
+
},
|
| 6708 |
+
"asr/sensevoice-sherpa-int8/tokens.txt": {
|
| 6709 |
+
"bytes": 315894,
|
| 6710 |
+
"sha256": "f449eb28dc567533d7fa59be34e2abca8784f771850c78a47fb731a31429a1dc",
|
| 6711 |
+
"source_group": "asr/sensevoice-sherpa-int8",
|
| 6712 |
+
"relative_path": "tokens.txt"
|
| 6713 |
+
},
|
| 6714 |
+
"mt/hy-mt2/Hy-MT2-1.8B-Q4_0-imat-q8emb-allq40.gguf": {
|
| 6715 |
+
"bytes": 1136777216,
|
| 6716 |
+
"sha256": "7bd3e18d8c02f70a0d99aa39724a8fcb5db5cc3f30872e5a907b44ca2498a4ca",
|
| 6717 |
+
"source_group": "mt/hy-mt2",
|
| 6718 |
+
"relative_path": "Hy-MT2-1.8B-Q4_0-imat-q8emb-allq40.gguf",
|
| 6719 |
+
"base_model": "tencent/Hy-MT2-1.8B@9a341cd1b679d3efd23b46e847b01745a71ed792",
|
| 6720 |
+
"format": "GGUF Q4_0 with imatrix and Q8 embedding"
|
| 6721 |
}
|
| 6722 |
},
|
| 6723 |
+
"total_bytes": 2034100362,
|
| 6724 |
+
"file_count": 1119
|
| 6725 |
}
|