patrickvonplaten commited on
Commit
90a6d44
1 Parent(s): a5df75d

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +44 -1
README.md CHANGED
@@ -59,4 +59,47 @@ To transcribe audio files the model can be used as a standalone acoustic model a
59
  # take argmax and decode
60
  predicted_ids = torch.argmax(logits, dim=-1)
61
  transcription = tokenizer.batch_decode(predicted_ids)
62
- ```
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
59
  # take argmax and decode
60
  predicted_ids = torch.argmax(logits, dim=-1)
61
  transcription = tokenizer.batch_decode(predicted_ids)
62
+ ```
63
+
64
+ ## Evaluation
65
+
66
+ This code snippet shows how to evaluate **facebook/wav2vec2-large-960h** on LibriSpeech's "clean" and "other" test data.
67
+
68
+ ```python
69
+ from datasets import load_dataset
70
+ from transformers import Wav2Vec2ForMaskedLM, Wav2Vec2Tokenizer
71
+ import soundfile as sf
72
+ import torch
73
+ from jiwer import wer
74
+
75
+
76
+ librispeech_eval = load_dataset("librispeech_asr", "clean", split="test")
77
+
78
+ model = Wav2Vec2ForMaskedLM.from_pretrained("facebook/wav2vec2-large-960h").to("cuda")
79
+ tokenizer = Wav2Vec2Tokenizer.from_pretrained("facebook/wav2vec2-base-960h")
80
+
81
+ def map_to_array(batch):
82
+ speech, _ = sf.read(batch["file"])
83
+ batch["speech"] = speech
84
+ return batch
85
+
86
+ librispeech_eval = librispeech_eval.map(map_to_array)
87
+
88
+ def map_to_pred(batch):
89
+ input_values = tokenizer(batch["speech"], return_tensors="pt", padding="longest").input_values
90
+ with torch.no_grad():
91
+ logits = model(input_values.to("cuda")).logits
92
+
93
+ predicted_ids = torch.argmax(logits, dim=-1)
94
+ transcription = tokenizer.batch_decode(predicted_ids)
95
+ batch["transcription"] = transcription
96
+ return batch
97
+
98
+ result = librispeech_eval.map(map_to_pred, batched=True, batch_size=16, remove_columns=["speech"])
99
+
100
+ print("WER:", wer(result["text"], result["transcription"]))
101
+ ```
102
+
103
+ | "clean" | "other" |
104
+ |---|---|
105
+ | 3.0 | 6.8 |