Instructions to use michael-chan-000/tts-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use michael-chan-000/tts-v2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-to-speech", model="michael-chan-000/tts-v2")# Load model directly from transformers import AutoProcessor, AutoModelForTextToWaveform processor = AutoProcessor.from_pretrained("michael-chan-000/tts-v2") model = AutoModelForTextToWaveform.from_pretrained("michael-chan-000/tts-v2") - Notebooks
- Google Colab
- Kaggle
| { | |
| "audio_bos_token": "<|audio_out_bos|>", | |
| "audio_delay_token": "<|reserved_special_token_6|>", | |
| "audio_eos_token": "<|audio_eos|>", | |
| "audio_stream_bos_id": 1024, | |
| "audio_stream_eos_id": 1025, | |
| "audio_token": "<|AUDIO_OUT|>", | |
| "audio_tokenizer": { | |
| "audio_tokenizer_class": "HiggsAudioV2TokenizerModel", | |
| "audio_tokenizer_name_or_path": "bosonai/higgs-audio-v2-tokenizer" | |
| }, | |
| "feature_extractor": { | |
| "feature_extractor_type": "DacFeatureExtractor", | |
| "feature_size": 1, | |
| "hop_length": 1, | |
| "padding_side": "right", | |
| "padding_value": 0.0, | |
| "return_attention_mask": true, | |
| "sampling_rate": 24000 | |
| }, | |
| "processor_class": "HiggsAudioV2Processor" | |
| } | |