facebook
/
wav2vec2-large-960h-lv60-self
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 2021-02-09 09:11:54 +00:00 committed by huggingface-web
parent aad7b2d146
commit 15bc8ce0fb
1 changed files with 4 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
README.md
View File

@ -30,14 +30,14 @@ 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: To transcribe audio files the model can be used as a standalone acoustic model as follows:
```python ```python
from transformers import Wav2Vec2Tokenizer, Wav2Vec2ForMaskedLM from transformers import Wav2Vec2Tokenizer, Wav2Vec2ForCTC
from datasets import load_dataset from datasets import load_dataset
import soundfile as sf import soundfile as sf
import torch import torch
# load model and tokenizer # load model and tokenizer
tokenizer = Wav2Vec2Tokenizer.from_pretrained("facebook/wav2vec2-large-960h-lv60-self") tokenizer = Wav2Vec2Tokenizer.from_pretrained("facebook/wav2vec2-large-960h-lv60-self")
model = Wav2Vec2ForMaskedLM.from_pretrained("facebook/wav2vec2-large-960h-lv60-self") model = Wav2Vec2ForCTC.from_pretrained("facebook/wav2vec2-large-960h-lv60-self")
# define function to read in sound file # define function to read in sound file
def map_to_array(batch): def map_to_array(batch):
@ -66,7 +66,7 @@ To transcribe audio files the model can be used as a standalone acoustic model a
```python ```python
from datasets import load_dataset from datasets import load_dataset
from transformers import Wav2Vec2ForMaskedLM, Wav2Vec2Tokenizer from transformers import Wav2Vec2ForCTC, Wav2Vec2Tokenizer
import soundfile as sf import soundfile as sf
import torch import torch
from jiwer import wer from jiwer import wer
@ -74,7 +74,7 @@ from jiwer import wer
librispeech_eval = load_dataset("librispeech_asr", "clean", split="test") librispeech_eval = load_dataset("librispeech_asr", "clean", split="test")
model = Wav2Vec2ForMaskedLM.from_pretrained("facebook/wav2vec2-large-960h-lv60-self").to("cuda") model = Wav2Vec2ForCTC.from_pretrained("facebook/wav2vec2-large-960h-lv60-self").to("cuda")
tokenizer = Wav2Vec2Tokenizer.from_pretrained("facebook/wav2vec2-base-960h-lv60-self") tokenizer = Wav2Vec2Tokenizer.from_pretrained("facebook/wav2vec2-base-960h-lv60-self")
def map_to_array(batch): def map_to_array(batch):