Audio-Text-to-Text
Transformers
Safetensors
vibevoice_asr
automatic-speech-recognition
ASR
Diarization
Speech-to-Text
Transcription
Instructions to use bezzam/VibeVoice-ASR-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use bezzam/VibeVoice-ASR-7B with Transformers:
# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("bezzam/VibeVoice-ASR-7B") model = AutoModelForMultimodalLM.from_pretrained("bezzam/VibeVoice-ASR-7B", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Upload VibeVoiceAsrForConditionalGeneration
Browse files- config.json +4 -2
- model-00007-of-00008.safetensors +2 -2
- model-00008-of-00008.safetensors +2 -2
- model.safetensors.index.json +0 -0
config.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"
|
| 3 |
"channels": 1,
|
| 4 |
"depths": [
|
| 5 |
3,
|
|
@@ -28,6 +28,7 @@
|
|
| 28 |
"model_type": "vibevoice_acoustic_tokenizer_encoder",
|
| 29 |
"num_filters": 32,
|
| 30 |
"rms_norm_eps": 1e-05,
|
|
|
|
| 31 |
"weight_init_value": 0.01
|
| 32 |
},
|
| 33 |
"acoustic_vae_std": 0.625,
|
|
@@ -39,7 +40,7 @@
|
|
| 39 |
"audio_token_id": 151648,
|
| 40 |
"dtype": "bfloat16",
|
| 41 |
"model_type": "vibevoice_asr",
|
| 42 |
-
"
|
| 43 |
"channels": 1,
|
| 44 |
"depths": [
|
| 45 |
3,
|
|
@@ -68,6 +69,7 @@
|
|
| 68 |
"model_type": "vibevoice_acoustic_tokenizer_encoder",
|
| 69 |
"num_filters": 32,
|
| 70 |
"rms_norm_eps": 1e-05,
|
|
|
|
| 71 |
"weight_init_value": 0.01
|
| 72 |
},
|
| 73 |
"text_config": {
|
|
|
|
| 1 |
{
|
| 2 |
+
"acoustic_tokenizer_encoder_config": {
|
| 3 |
"channels": 1,
|
| 4 |
"depths": [
|
| 5 |
3,
|
|
|
|
| 28 |
"model_type": "vibevoice_acoustic_tokenizer_encoder",
|
| 29 |
"num_filters": 32,
|
| 30 |
"rms_norm_eps": 1e-05,
|
| 31 |
+
"vae_std": 0.625,
|
| 32 |
"weight_init_value": 0.01
|
| 33 |
},
|
| 34 |
"acoustic_vae_std": 0.625,
|
|
|
|
| 40 |
"audio_token_id": 151648,
|
| 41 |
"dtype": "bfloat16",
|
| 42 |
"model_type": "vibevoice_asr",
|
| 43 |
+
"semantic_tokenizer_encoder_config": {
|
| 44 |
"channels": 1,
|
| 45 |
"depths": [
|
| 46 |
3,
|
|
|
|
| 69 |
"model_type": "vibevoice_acoustic_tokenizer_encoder",
|
| 70 |
"num_filters": 32,
|
| 71 |
"rms_norm_eps": 1e-05,
|
| 72 |
+
"vae_std": 0.625,
|
| 73 |
"weight_init_value": 0.01
|
| 74 |
},
|
| 75 |
"text_config": {
|
model-00007-of-00008.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b52aa2fab9640bcac5201a278f540b018c439ed4e99516d9ff30ea1ae399525e
|
| 3 |
+
size 2482226384
|
model-00008-of-00008.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a66ced85b619507e1970dc51be45786ff55803ccc63658765e412ea23d9a8ace
|
| 3 |
+
size 37262376
|
model.safetensors.index.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|