Automatic Speech Recognition
Transformers
ONNX
Safetensors
ASR
Transcriptoin
Diarization
Speech-to-Text
Instructions to use Prince-1/VibeVoice with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Prince-1/VibeVoice with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="Prince-1/VibeVoice")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Prince-1/VibeVoice", dtype="auto") - Notebooks
- Google Colab
- Kaggle
Add files using upload-large-folder tool
Browse files- .gitattributes +1 -0
- onnx/genai_config.json +49 -0
- onnx/model.onnx +3 -0
- onnx/model.onnx.data +3 -0
- onnx/tokenizer.json +84 -0
- onnx/tokenizer_config.json +12 -0
.gitattributes
CHANGED
|
@@ -35,3 +35,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
figures/language_distribution_horizontal.png filter=lfs diff=lfs merge=lfs -text
|
| 37 |
figures/VibeVoice_ASR_archi.png filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
figures/language_distribution_horizontal.png filter=lfs diff=lfs merge=lfs -text
|
| 37 |
figures/VibeVoice_ASR_archi.png filter=lfs diff=lfs merge=lfs -text
|
| 38 |
+
onnx/model.onnx.data filter=lfs diff=lfs merge=lfs -text
|
onnx/genai_config.json
ADDED
|
@@ -0,0 +1,49 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"model": {
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"context_length": 131072,
|
| 5 |
+
"decoder": {
|
| 6 |
+
"session_options": {
|
| 7 |
+
"log_id": "onnxruntime-genai",
|
| 8 |
+
"provider_options": []
|
| 9 |
+
},
|
| 10 |
+
"filename": "model.onnx",
|
| 11 |
+
"head_size": 128,
|
| 12 |
+
"hidden_size": 3584,
|
| 13 |
+
"inputs": {
|
| 14 |
+
"input_ids": "input_ids",
|
| 15 |
+
"attention_mask": "attention_mask",
|
| 16 |
+
"position_ids": "position_ids",
|
| 17 |
+
"past_key_names": "past_key_values.%d.key",
|
| 18 |
+
"past_value_names": "past_key_values.%d.value"
|
| 19 |
+
},
|
| 20 |
+
"outputs": {
|
| 21 |
+
"present_key_names": "present.%d.key",
|
| 22 |
+
"present_value_names": "present.%d.value"
|
| 23 |
+
},
|
| 24 |
+
"num_attention_heads": 28,
|
| 25 |
+
"num_hidden_layers": 28,
|
| 26 |
+
"num_key_value_heads": 4
|
| 27 |
+
},
|
| 28 |
+
"eos_token_id": null,
|
| 29 |
+
"pad_token_id": null,
|
| 30 |
+
"type": "qwen2",
|
| 31 |
+
"vocab_size": 152064
|
| 32 |
+
},
|
| 33 |
+
"search": {
|
| 34 |
+
"diversity_penalty": 0.0,
|
| 35 |
+
"do_sample": false,
|
| 36 |
+
"early_stopping": true,
|
| 37 |
+
"length_penalty": 1.0,
|
| 38 |
+
"max_length": 131072,
|
| 39 |
+
"min_length": 0,
|
| 40 |
+
"no_repeat_ngram_size": 0,
|
| 41 |
+
"num_beams": 1,
|
| 42 |
+
"num_return_sequences": 1,
|
| 43 |
+
"past_present_share_buffer": false,
|
| 44 |
+
"repetition_penalty": 1.0,
|
| 45 |
+
"temperature": 1.0,
|
| 46 |
+
"top_k": 50,
|
| 47 |
+
"top_p": 1.0
|
| 48 |
+
}
|
| 49 |
+
}
|
onnx/model.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f1c41f7cba7557fe5e6c17bf0cdd3fc0fdde800320c03546ae0035cd6ff75b98
|
| 3 |
+
size 692031
|
onnx/model.onnx.data
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4f5e93c442a1a979df07fc2a04595adbb70800941f7be07a6e3cf4d64f17de8d
|
| 3 |
+
size 14174846976
|
onnx/tokenizer.json
ADDED
|
@@ -0,0 +1,84 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"version": "1.0",
|
| 3 |
+
"truncation": null,
|
| 4 |
+
"padding": null,
|
| 5 |
+
"added_tokens": [
|
| 6 |
+
{
|
| 7 |
+
"id": 0,
|
| 8 |
+
"content": "<|endoftext|>",
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"lstrip": false,
|
| 11 |
+
"rstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"special": true
|
| 14 |
+
}
|
| 15 |
+
],
|
| 16 |
+
"normalizer": {
|
| 17 |
+
"type": "NFC"
|
| 18 |
+
},
|
| 19 |
+
"pre_tokenizer": {
|
| 20 |
+
"type": "Sequence",
|
| 21 |
+
"pretokenizers": [
|
| 22 |
+
{
|
| 23 |
+
"type": "Split",
|
| 24 |
+
"pattern": {
|
| 25 |
+
"Regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?\\p{L}+|\\p{N}| ?[^\\s\\p{L}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+"
|
| 26 |
+
},
|
| 27 |
+
"behavior": "Isolated",
|
| 28 |
+
"invert": false
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"type": "ByteLevel",
|
| 32 |
+
"add_prefix_space": false,
|
| 33 |
+
"trim_offsets": true,
|
| 34 |
+
"use_regex": false
|
| 35 |
+
}
|
| 36 |
+
]
|
| 37 |
+
},
|
| 38 |
+
"post_processor": {
|
| 39 |
+
"type": "TemplateProcessing",
|
| 40 |
+
"single": [
|
| 41 |
+
{
|
| 42 |
+
"Sequence": {
|
| 43 |
+
"id": "A",
|
| 44 |
+
"type_id": 0
|
| 45 |
+
}
|
| 46 |
+
}
|
| 47 |
+
],
|
| 48 |
+
"pair": [
|
| 49 |
+
{
|
| 50 |
+
"Sequence": {
|
| 51 |
+
"id": "A",
|
| 52 |
+
"type_id": 0
|
| 53 |
+
}
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"Sequence": {
|
| 57 |
+
"id": "B",
|
| 58 |
+
"type_id": 1
|
| 59 |
+
}
|
| 60 |
+
}
|
| 61 |
+
],
|
| 62 |
+
"special_tokens": {}
|
| 63 |
+
},
|
| 64 |
+
"decoder": {
|
| 65 |
+
"type": "ByteLevel",
|
| 66 |
+
"add_prefix_space": true,
|
| 67 |
+
"trim_offsets": true,
|
| 68 |
+
"use_regex": true
|
| 69 |
+
},
|
| 70 |
+
"model": {
|
| 71 |
+
"type": "BPE",
|
| 72 |
+
"dropout": null,
|
| 73 |
+
"unk_token": null,
|
| 74 |
+
"continuing_subword_prefix": "",
|
| 75 |
+
"end_of_word_suffix": "",
|
| 76 |
+
"fuse_unk": false,
|
| 77 |
+
"byte_fallback": false,
|
| 78 |
+
"ignore_merges": false,
|
| 79 |
+
"vocab": {
|
| 80 |
+
"<|endoftext|>": 0
|
| 81 |
+
},
|
| 82 |
+
"merges": []
|
| 83 |
+
}
|
| 84 |
+
}
|
onnx/tokenizer_config.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": null,
|
| 3 |
+
"backend": "tokenizers",
|
| 4 |
+
"bos_token": null,
|
| 5 |
+
"eos_token": "<|endoftext|>",
|
| 6 |
+
"is_local": true,
|
| 7 |
+
"local_files_only": false,
|
| 8 |
+
"model_max_length": 131072,
|
| 9 |
+
"pad_token": "<|endoftext|>",
|
| 10 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 11 |
+
"unk_token": "<|endoftext|>"
|
| 12 |
+
}
|