facebook
/
wav2vec2-base-960h
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Update README.md

This commit is contained in:
Patrick von Platen 2021-08-27 15:30:05 +00:00 committed by huggingface-web
parent 67fb590898
commit f1f16470cc
1 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
README.md
View File

@ -36,13 +36,13 @@ The original model can be found under https://github.com/pytorch/fairseq/tree/ma
To transcribe audio files the model can be used as a standalone acoustic model as follows:
```python
from transformers import Wav2Vec2Tokenizer, Wav2Vec2ForCTC
from transformers import Wav2Vec2CTCTokenizer, Wav2Vec2ForCTC
from datasets import load_dataset
import soundfile as sf
import torch
# load model and tokenizer
tokenizer = Wav2Vec2Tokenizer.from_pretrained("facebook/wav2vec2-base-960h")
tokenizer = Wav2Vec2CTCTokenizer.from_pretrained("facebook/wav2vec2-base-960h")
model = Wav2Vec2ForCTC.from_pretrained("facebook/wav2vec2-base-960h")
# define function to read in sound file
@ -81,7 +81,7 @@ from jiwer import wer
librispeech_eval = load_dataset("librispeech_asr", "clean", split="test")
model = Wav2Vec2ForCTC.from_pretrained("facebook/wav2vec2-base-960h").to("cuda")
tokenizer = Wav2Vec2Tokenizer.from_pretrained("facebook/wav2vec2-base-960h")
tokenizer = Wav2Vec2CTCTokenizer.from_pretrained("facebook/wav2vec2-base-960h")
def map_to_array(batch):
speech, _ = sf.read(batch["file"])