Hugging Face's logo

microsoft
/
wavlm-base-sv

Transformers PyTorch English wavlm audio-xvector speech Inference Endpoints
Model card Files Community
anton-l HF staff commited on
Commit
0a23162
•
1 Parent(s): 1616a77

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -3
README.md CHANGED
@@ -1,7 +1,6 @@
1
  ---
2
  language:
3
  - en
4
- datasets:
5
  tags:
6
  - speech
7
  ---
@@ -30,13 +29,13 @@ The model is fine-tuned on the [VoxCeleb1 dataset](https://www.robots.ox.ac.uk/~
30
  # Usage
31
  ## Speaker Verification
32
  ```python
33
- from transformers import Wav2Vec2FeatureExtractor, UniSpeechSatForXVector
34
  from datasets import load_dataset
35
  import torch
36
 
37
  dataset = load_dataset("hf-internal-testing/librispeech_asr_demo", "clean", split="validation")
38
  feature_extractor = Wav2Vec2FeatureExtractor.from_pretrained('microsoft/wavlm-base-sv')
39
- model = UniSpeechSatForXVector.from_pretrained('microsoft/wavlm-base-sv')
40
 
41
  # audio files are decoded on the fly
42
  inputs = feature_extractor(dataset[:2]["audio"]["array"], return_tensors="pt")
1
  ---
2
  language:
3
  - en
 
4
  tags:
5
  - speech
6
  ---
29
  # Usage
30
  ## Speaker Verification
31
  ```python
32
+ from transformers import Wav2Vec2FeatureExtractor, WavLMForXVector
33
  from datasets import load_dataset
34
  import torch
35
 
36
  dataset = load_dataset("hf-internal-testing/librispeech_asr_demo", "clean", split="validation")
37
  feature_extractor = Wav2Vec2FeatureExtractor.from_pretrained('microsoft/wavlm-base-sv')
38
+ model = WavLMForXVector.from_pretrained('microsoft/wavlm-base-sv')
39
 
40
  # audio files are decoded on the fly
41
  inputs = feature_extractor(dataset[:2]["audio"]["array"], return_tensors="pt")