Instructions to use multimodalart/VibeVoice-ASR-BitNet-ONNX with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers.js
How to use multimodalart/VibeVoice-ASR-BitNet-ONNX with Transformers.js:
// npm i @huggingface/transformers import { pipeline } from '@huggingface/transformers'; // Allocate pipeline const pipe = await pipeline('automatic-speech-recognition', 'multimodalart/VibeVoice-ASR-BitNet-ONNX');
Upload folder using huggingface_hub
Browse files- conversion_report.json +16 -1
- onnx/audio_encoder_fp16.onnx +3 -0
- onnx/audio_encoder_q4.onnx +3 -0
- onnx/audio_encoder_q4f16.onnx +3 -0
- onnx/decoder_model_merged_bnb4.onnx +3 -0
- onnx/decoder_model_merged_q4.onnx +3 -0
- onnx/decoder_model_merged_q4f16.onnx +3 -0
- onnx/embed_tokens_fp16.onnx +3 -0
- onnx/embed_tokens_q4.onnx +3 -0
- onnx/embed_tokens_q4f16.onnx +3 -0
conversion_report.json
CHANGED
|
@@ -28,5 +28,20 @@
|
|
| 28 |
}
|
| 29 |
},
|
| 30 |
"validation": {},
|
| 31 |
-
"sizes": {
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 32 |
}
|
|
|
|
| 28 |
}
|
| 29 |
},
|
| 30 |
"validation": {},
|
| 31 |
+
"sizes": {
|
| 32 |
+
"audio_encoder.onnx_data": 2773.3,
|
| 33 |
+
"audio_encoder.onnx": 0.4,
|
| 34 |
+
"embed_tokens.onnx": 933.5,
|
| 35 |
+
"decoder_model_merged.onnx_data": 6174.9,
|
| 36 |
+
"decoder_model_merged.onnx": 0.5,
|
| 37 |
+
"audio_encoder_fp16.onnx": 1387.0,
|
| 38 |
+
"audio_encoder_q4.onnx": 696.4,
|
| 39 |
+
"audio_encoder_q4f16.onnx": 694.9,
|
| 40 |
+
"embed_tokens_q4.onnx": 234.0,
|
| 41 |
+
"embed_tokens_q4f16.onnx": 233.7,
|
| 42 |
+
"embed_tokens_fp16.onnx": 466.7,
|
| 43 |
+
"decoder_model_merged_q4.onnx": 1054.0,
|
| 44 |
+
"decoder_model_merged_q4f16.onnx": 869.1,
|
| 45 |
+
"decoder_model_merged_bnb4.onnx": 726.4
|
| 46 |
+
}
|
| 47 |
}
|
onnx/audio_encoder_fp16.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:82f9c393cbfc1238057ee62c7c23369105946287a3ef1e47a796e643e95ea29c
|
| 3 |
+
size 1387031861
|
onnx/audio_encoder_q4.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:516787f786cefd4c5c6aa6b98f9ca63df2e8bc4f97eea6f302f0e14913b7466b
|
| 3 |
+
size 696362711
|
onnx/audio_encoder_q4f16.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:502d569cbbca176b61c7ebe7f62e4d99ab97d156bbaa9ee34e754f3de7bb37cb
|
| 3 |
+
size 694864453
|
onnx/decoder_model_merged_bnb4.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5973c85b32d126b77091176dbdf0324edd49c0e43c7f317f7d084e3379ff4df3
|
| 3 |
+
size 726430878
|
onnx/decoder_model_merged_q4.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:396e5b966889ecf829cd8228260810c7027106ae21a93536de442804e6ff491d
|
| 3 |
+
size 1053979806
|
onnx/decoder_model_merged_q4f16.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e0334884a28d0ab96578918e66bd0e6ad09e5b79677b52814e2f939eddb23ca9
|
| 3 |
+
size 869093546
|
onnx/embed_tokens_fp16.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c8678af863eb5ebd28f8326d78916297b7d5d55c0126966779c321cec3978f0b
|
| 3 |
+
size 466747622
|
onnx/embed_tokens_q4.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ffd6c9d4b91850ef254dea10644efca3753eae8a14a22cc41415ab7097c0b6e2
|
| 3 |
+
size 233981821
|
onnx/embed_tokens_q4f16.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8e1a5fa0218ffa89cc6e1d4c0a6e0bf5b9e67c47b63452d956ab13eb0011f192
|
| 3 |
+
size 233677949
|