Hugging Face's logo

microsoft
/
wavlm-base-plus-sd

Transformers PyTorch English wavlm audio-frame-classification speech Inference Endpoints 4 papers
Model card Files Community
1
anton-l HF staff commited on
Commit
5bd86f0
•
1 Parent(s): a943bef

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
  ---
@@ -33,13 +32,13 @@ The model is fine-tuned on the [LibriMix dataset](https://github.com/JorisCos/Li
33
  # Usage
34
  ## Speaker Diarization
35
  ```python
36
- from transformers import Wav2Vec2FeatureExtractor, UniSpeechSatForAudioFrameClassification
37
  from datasets import load_dataset
38
  import torch
39
 
40
  dataset = load_dataset("hf-internal-testing/librispeech_asr_demo", "clean", split="validation")
41
  feature_extractor = Wav2Vec2FeatureExtractor.from_pretrained('microsoft/wavlm-base-plus-sd')
42
- model = UniSpeechSatForAudioFrameClassification.from_pretrained('microsoft/wavlm-base-plus-sd')
43
 
44
  # audio file is decoded on the fly
45
  inputs = feature_extractor(dataset[0]["audio"]["array"], return_tensors="pt")
1
  ---
2
  language:
3
  - en
 
4
  tags:
5
  - speech
6
  ---
32
  # Usage
33
  ## Speaker Diarization
34
  ```python
35
+ from transformers import Wav2Vec2FeatureExtractor, WavLMForAudioFrameClassification
36
  from datasets import load_dataset
37
  import torch
38
 
39
  dataset = load_dataset("hf-internal-testing/librispeech_asr_demo", "clean", split="validation")
40
  feature_extractor = Wav2Vec2FeatureExtractor.from_pretrained('microsoft/wavlm-base-plus-sd')
41
+ model = WavLMForAudioFrameClassification.from_pretrained('microsoft/wavlm-base-plus-sd')
42
 
43
  # audio file is decoded on the fly
44
  inputs = feature_extractor(dataset[0]["audio"]["array"], return_tensors="pt")