From c0b7a4ab9dcf6b5ddb2ebad1ae045702a21d0f47 Mon Sep 17 00:00:00 2001
From: Patrick von Platen <patrick.v.platen@gmail.com>
Date: Tue, 5 Apr 2022 16:39:29 +0000
Subject: [PATCH] Update README.md

---
 README.md | 10 +---------
 1 file changed, 1 insertion(+), 9 deletions(-)

diff --git a/README.md b/README.md
index 9a31ab8..75331f3 100644
--- a/README.md
+++ b/README.md
@@ -81,7 +81,6 @@ To transcribe audio files the model can be used as a standalone acoustic model a
 ```python
 from datasets import load_dataset
 from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
-import soundfile as sf
 import torch
 from jiwer import wer
 
@@ -91,15 +90,8 @@ librispeech_eval = load_dataset("librispeech_asr", "clean", split="test")
 model = Wav2Vec2ForCTC.from_pretrained("facebook/wav2vec2-base-960h").to("cuda")
 processor = Wav2Vec2Processor.from_pretrained("facebook/wav2vec2-base-960h")
 
-def map_to_array(batch):
-    speech, _ = sf.read(batch["file"])
-    batch["speech"] = speech
-    return batch
-
-librispeech_eval = librispeech_eval.map(map_to_array)
-
 def map_to_pred(batch):
-    input_values = processor(batch["speech"], return_tensors="pt", padding="longest").input_values
+    input_values = processor(batch["audio"]["array"], return_tensors="pt", padding="longest").input_values
     with torch.no_grad():
         logits = model(input_values.to("cuda")).logits