Text-to-Speech
Transformers
Safetensors
MLX
higgs_multimodal_qwen3
text-generation
speech-generation
higgs-audio
qwen3
quantization
4-bit precision
Instructions to use Reza2kn/Higgs-Audio-v3-TTS-4bit-MLX with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Reza2kn/Higgs-Audio-v3-TTS-4bit-MLX with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-to-speech", model="Reza2kn/Higgs-Audio-v3-TTS-4bit-MLX")# Load model directly from transformers import AutoModelForSeq2SeqLM model = AutoModelForSeq2SeqLM.from_pretrained("Reza2kn/Higgs-Audio-v3-TTS-4bit-MLX", device_map="auto") - MLX
How to use Reza2kn/Higgs-Audio-v3-TTS-4bit-MLX with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir Higgs-Audio-v3-TTS-4bit-MLX Reza2kn/Higgs-Audio-v3-TTS-4bit-MLX
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
Add functional quant test report
Browse files
coreml_transformers_blocker_probe.json
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"model": "/Users/studio/higgs-audio/base_full",
|
| 3 |
+
"attempts": [
|
| 4 |
+
{
|
| 5 |
+
"name": "AutoConfig",
|
| 6 |
+
"ok": false,
|
| 7 |
+
"error": "ValueError('The checkpoint you are trying to load has model type `higgs_multimodal_qwen3` but Transformers does not recognize this architecture. This could be because of an issue with the checkpoint, or because your version of Transformers is out of date.\\n\\nYou can update Transformers with the command `pip install --upgrade transformers`. If this does not work, and the checkpoint is very new, then there may not be a release version that supports this model yet. In this case, you can get the most up-to-date code by installing Transformers from source with the command `pip install git+https://github.com/huggingface/transformers.git`')"
|
| 8 |
+
},
|
| 9 |
+
{
|
| 10 |
+
"name": "AutoProcessor",
|
| 11 |
+
"ok": true,
|
| 12 |
+
"class": "Qwen2Tokenizer"
|
| 13 |
+
},
|
| 14 |
+
{
|
| 15 |
+
"name": "AutoModelForCausalLM",
|
| 16 |
+
"ok": false,
|
| 17 |
+
"error": "ValueError('The checkpoint you are trying to load has model type `higgs_multimodal_qwen3` but Transformers does not recognize this architecture. This could be because of an issue with the checkpoint, or because your version of Transformers is out of date.\\n\\nYou can update Transformers with the command `pip install --upgrade transformers`. If this does not work, and the checkpoint is very new, then there may not be a release version that supports this model yet. In this case, you can get the most up-to-date code by installing Transformers from source with the command `pip install git+https://github.com/huggingface/transformers.git`')"
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"name": "AutoModelForTextToWaveform",
|
| 21 |
+
"ok": false,
|
| 22 |
+
"error": "ValueError('The checkpoint you are trying to load has model type `higgs_multimodal_qwen3` but Transformers does not recognize this architecture. This could be because of an issue with the checkpoint, or because your version of Transformers is out of date.\\n\\nYou can update Transformers with the command `pip install --upgrade transformers`. If this does not work, and the checkpoint is very new, then there may not be a release version that supports this model yet. In this case, you can get the most up-to-date code by installing Transformers from source with the command `pip install git+https://github.com/huggingface/transformers.git`')"
|
| 23 |
+
}
|
| 24 |
+
]
|
| 25 |
+
}
|