Instructions to use eustlb/higgs-v2-archive with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use eustlb/higgs-v2-archive with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-to-audio", model="eustlb/higgs-v2-archive")# Load model directly from transformers import AutoProcessor, AutoModelForTextToWaveform processor = AutoProcessor.from_pretrained("eustlb/higgs-v2-archive") model = AutoModelForTextToWaveform.from_pretrained("eustlb/higgs-v2-archive") - Notebooks
- Google Colab
- Kaggle
Upload tokenizer
Browse files- special_tokens_map.json +2 -1
- tokenizer_config.json +1 -0
special_tokens_map.json
CHANGED
|
@@ -12,5 +12,6 @@
|
|
| 12 |
"normalized": false,
|
| 13 |
"rstrip": false,
|
| 14 |
"single_word": false
|
| 15 |
-
}
|
|
|
|
| 16 |
}
|
|
|
|
| 12 |
"normalized": false,
|
| 13 |
"rstrip": false,
|
| 14 |
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "<|end_of_text|>"
|
| 17 |
}
|
tokenizer_config.json
CHANGED
|
@@ -2058,6 +2058,7 @@
|
|
| 2058 |
"attention_mask"
|
| 2059 |
],
|
| 2060 |
"model_max_length": 131072,
|
|
|
|
| 2061 |
"processor_class": "HiggsAudioV2Processor",
|
| 2062 |
"tokenizer_class": "PreTrainedTokenizerFast",
|
| 2063 |
"trust_remote": true
|
|
|
|
| 2058 |
"attention_mask"
|
| 2059 |
],
|
| 2060 |
"model_max_length": 131072,
|
| 2061 |
+
"pad_token": "<|end_of_text|>",
|
| 2062 |
"processor_class": "HiggsAudioV2Processor",
|
| 2063 |
"tokenizer_class": "PreTrainedTokenizerFast",
|
| 2064 |
"trust_remote": true
|