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- generation_config.json +5 -0
generation_config.json
CHANGED
|
@@ -1,7 +1,12 @@
|
|
| 1 |
{
|
| 2 |
"_from_model_config": true,
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
"output_attentions": false,
|
| 4 |
"output_hidden_states": false,
|
|
|
|
| 5 |
"transformers_version": "5.0.1.dev0",
|
| 6 |
"use_cache": true
|
| 7 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"_from_model_config": true,
|
| 3 |
+
"do_sample": false,
|
| 4 |
+
"eos_token_id": 151643,
|
| 5 |
+
"max_length": 32768,
|
| 6 |
+
"max_new_tokens": 32768,
|
| 7 |
"output_attentions": false,
|
| 8 |
"output_hidden_states": false,
|
| 9 |
+
"pad_token_id": 151655,
|
| 10 |
"transformers_version": "5.0.1.dev0",
|
| 11 |
"use_cache": true
|
| 12 |
}
|