Adding `safetensors` variant of this model (#7)

- Adding `safetensors` variant of this model (b593867a0567fe9d5be38a6746b2932feaf52894)


Co-authored-by: Nicolas Patry <Narsil@users.noreply.huggingface.co>

.gitattributes

@@ -15,3 +15,4 @@
 *.pt filter=lfs diff=lfs merge=lfs -text
 *.pth filter=lfs diff=lfs merge=lfs -text
 *.msgpack filter=lfs diff=lfs merge=lfs -text
+model.safetensors filter=lfs diff=lfs merge=lfs -text

README.md

@@ -5,12 +5,44 @@ datasets:
 tags:
 - audio
 - automatic-speech-recognition
+- hf-asr-leaderboard
 license: apache-2.0
 widget:
-- label: Librispeech sample 1
+- example_title: Librispeech sample 1
   src: https://cdn-media.huggingface.co/speech_samples/sample1.flac
-- label: Librispeech sample 2
+- example_title: Librispeech sample 2
   src: https://cdn-media.huggingface.co/speech_samples/sample2.flac
+model-index:
+- name: wav2vec2-base-960h
+  results:
+  - task:
+      name: Automatic Speech Recognition
+      type: automatic-speech-recognition
+    dataset:
+      name: LibriSpeech (clean)
+      type: librispeech_asr
+      config: clean
+      split: test
+      args: 
+        language: en
+    metrics:
+    - name: Test WER
+      type: wer
+      value: 3.4
+  - task:
+      name: Automatic Speech Recognition
+      type: automatic-speech-recognition
+    dataset:
+      name: LibriSpeech (other)
+      type: librispeech_asr
+      config: other
+      split: test
+      args: 
+        language: en
+    metrics:
+    - name: Test WER
+      type: wer
+      value: 8.6
 ---
 
 # Wav2Vec2-Base-960h
@@ -36,34 +68,26 @@ 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 Wav2Vec2CTCTokenizer, Wav2Vec2ForCTC
+ from transformers import Wav2Vec2Processor, Wav2Vec2ForCTC
  from datasets import load_dataset
- import soundfile as sf
  import torch
  
  # load model and tokenizer
- tokenizer = Wav2Vec2CTCTokenizer.from_pretrained("facebook/wav2vec2-base-960h")
+ processor = Wav2Vec2Processor.from_pretrained("facebook/wav2vec2-base-960h")
  model = Wav2Vec2ForCTC.from_pretrained("facebook/wav2vec2-base-960h")
      
- # define function to read in sound file
- def map_to_array(batch):
-     speech, _ = sf.read(batch["file"])
-     batch["speech"] = speech
-     return batch
-     
  # load dummy dataset and read soundfiles
  ds = load_dataset("patrickvonplaten/librispeech_asr_dummy", "clean", split="validation")
- ds = ds.map(map_to_array)
  
  # tokenize
- input_values = tokenizer(ds["speech"][:2], return_tensors="pt", padding="longest").input_values  # Batch size 1
+ input_values = processor(ds[0]["audio"]["array"], return_tensors="pt", padding="longest").input_values  # Batch size 1
  
  # retrieve logits
  logits = model(input_values).logits
  
  # take argmax and decode
  predicted_ids = torch.argmax(logits, dim=-1)
- transcription = tokenizer.batch_decode(predicted_ids)
+ transcription = processor.batch_decode(predicted_ids)
  ```
  
  ## Evaluation
@@ -72,8 +96,7 @@ 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, Wav2Vec2Tokenizer
-import soundfile as sf
+from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
 import torch
 from jiwer import wer
 
@@ -81,26 +104,19 @@ from jiwer import wer
 librispeech_eval = load_dataset("librispeech_asr", "clean", split="test")
 
 model = Wav2Vec2ForCTC.from_pretrained("facebook/wav2vec2-base-960h").to("cuda")
-tokenizer = Wav2Vec2CTCTokenizer.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)
+processor = Wav2Vec2Processor.from_pretrained("facebook/wav2vec2-base-960h")
 
 def map_to_pred(batch):
-    input_values = tokenizer(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
 
     predicted_ids = torch.argmax(logits, dim=-1)
-    transcription = tokenizer.batch_decode(predicted_ids)
+    transcription = processor.batch_decode(predicted_ids)
     batch["transcription"] = transcription
     return batch
 
-result = librispeech_eval.map(map_to_pred, batched=True, batch_size=1, remove_columns=["speech"])
+result = librispeech_eval.map(map_to_pred, batched=True, batch_size=1, remove_columns=["audio"])
 
 print("WER:", wer(result["text"], result["transcription"]))
 ```