Automatic Speech Recognition
GGUF
VibeVoice
ggml
audio
speech-recognition
transcription
diarization
speaker-diarization
timestamps
hotwords
qwen2
speech-llm
multilingual
long-form
Instructions to use cstr/vibevoice-asr-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- VibeVoice
How to use cstr/vibevoice-asr-GGUF with VibeVoice:
import torch, soundfile as sf, librosa, numpy as np from vibevoice.processor.vibevoice_processor import VibeVoiceProcessor from vibevoice.modular.modeling_vibevoice_inference import VibeVoiceForConditionalGenerationInference # Load voice sample (should be 24kHz mono) voice, sr = sf.read("path/to/voice_sample.wav") if voice.ndim > 1: voice = voice.mean(axis=1) if sr != 24000: voice = librosa.resample(voice, sr, 24000) processor = VibeVoiceProcessor.from_pretrained("cstr/vibevoice-asr-GGUF") model = VibeVoiceForConditionalGenerationInference.from_pretrained( "cstr/vibevoice-asr-GGUF", torch_dtype=torch.bfloat16 ).to("cuda").eval() model.set_ddpm_inference_steps(5) inputs = processor(text=["Speaker 0: Hello!\nSpeaker 1: Hi there!"], voice_samples=[[voice]], return_tensors="pt") audio = model.generate(**inputs, cfg_scale=1.3, tokenizer=processor.tokenizer).speech_outputs[0] sf.write("output.wav", audio.cpu().numpy().squeeze(), 24000) - Notebooks
- Google Colab
- Kaggle
Add diff-harness reference dump vibevoice-ref-jfk.gguf
Browse files
.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 |
vibevoice-asr-q4_k.gguf filter=lfs diff=lfs merge=lfs -text
|
| 37 |
vibevoice-asr-f16.gguf filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
vibevoice-asr-q4_k.gguf filter=lfs diff=lfs merge=lfs -text
|
| 37 |
vibevoice-asr-f16.gguf filter=lfs diff=lfs merge=lfs -text
|
| 38 |
+
diff-harness-ref/vibevoice-ref-jfk.gguf filter=lfs diff=lfs merge=lfs -text
|
diff-harness-ref/vibevoice-ref-jfk.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5d399ac5805ee8e7b031204278a3d14db4af348db876b32b4caf8bf6b47572ed
|
| 3 |
+
size 4711552
|