Audio-Text-to-Text
Transformers
Safetensors
vibevoice_asr
automatic-speech-recognition
ASR
Diarization
Speech-to-Text
Transcription
Eval Results
Instructions to use microsoft/VibeVoice-ASR-HF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use microsoft/VibeVoice-ASR-HF with Transformers:
# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("microsoft/VibeVoice-ASR-HF") model = AutoModelForMultimodalLM.from_pretrained("microsoft/VibeVoice-ASR-HF", device_map="auto") - Notebooks
- Google Colab
- Kaggle
File size: 2,920 Bytes
8623f43 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 | {
"acoustic_tokenizer_chunk_size": 1440000,
"acoustic_tokenizer_encoder_config": {
"channels": 1,
"depths": [
3,
3,
3,
3,
3,
3,
8
],
"downsampling_ratios": [
2,
2,
4,
5,
5,
8
],
"dtype": "bfloat16",
"ffn_expansion": 4,
"hidden_act": "gelu",
"hidden_size": 64,
"initializer_range": 0.01,
"kernel_size": 7,
"layer_scale_init_value": 1e-06,
"model_type": "vibevoice_acoustic_tokenizer_encoder",
"num_filters": 32,
"rms_norm_eps": 1e-05,
"vae_std": 0.625,
"weight_init_value": 0.01
},
"architectures": [
"VibeVoiceAsrForConditionalGeneration"
],
"audio_bos_token_id": 151646,
"audio_eos_token_id": 151647,
"audio_token_id": 151648,
"dtype": "bfloat16",
"model_type": "vibevoice_asr",
"semantic_tokenizer_encoder_config": {
"channels": 1,
"depths": [
3,
3,
3,
3,
3,
3,
8
],
"downsampling_ratios": [
2,
2,
4,
5,
5,
8
],
"dtype": "bfloat16",
"ffn_expansion": 4,
"hidden_act": "gelu",
"hidden_size": 128,
"initializer_range": 0.01,
"kernel_size": 7,
"layer_scale_init_value": 1e-06,
"model_type": "vibevoice_acoustic_tokenizer_encoder",
"num_filters": 32,
"rms_norm_eps": 1e-05,
"vae_std": 0.625,
"weight_init_value": 0.01
},
"text_config": {
"attention_dropout": 0.0,
"bos_token_id": null,
"dtype": "bfloat16",
"eos_token_id": null,
"hidden_act": "silu",
"hidden_size": 3584,
"initializer_range": 0.02,
"intermediate_size": 18944,
"layer_types": [
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention"
],
"max_position_embeddings": 131072,
"max_window_layers": 28,
"model_type": "qwen2",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"pad_token_id": null,
"rms_norm_eps": 1e-06,
"rope_parameters": {
"rope_theta": 1000000.0,
"rope_type": "default"
},
"sliding_window": null,
"tie_word_embeddings": false,
"use_cache": true,
"use_mrope": false,
"use_sliding_window": false,
"vocab_size": 152064
},
"transformers_version": "5.3.0.dev0"
}
|