Merge branch 'main' of https://huggingface.co/KBLab/wav2vec2-large-voxrex-swedish into main

README.md

@@ -0,0 +1,65 @@
+---
+language: sv-SE
+datasets:
+- common_voice
+- NST Swedish ASR Database
+- P4
+metrics:
+- wer
+tags:
+- audio
+- automatic-speech-recognition
+- speech
+license: cc0
+model-index:
+- name: Wav2vec 2.0 large VoxRex Swedish
+  results:
+  - task: 
+      name: Speech Recognition
+      type: automatic-speech-recognition
+    dataset:
+      name: Common Voice
+      type: common_voice
+      args: sv-SE
+    metrics:
+       - name: Test WER
+         type: wer
+         value: 9.914
+---
+# Wav2vec 2.0 large VoxRex Swedish
+
+Finetuned version of KBs [VoxRex large](https://huggingface.co/KBLab/wav2vec2-large-voxrex) model using Swedish radio broadcasts, NST and Common Voice data. Evalutation without a language model gives the following: WER for NST + Common Voice test set (2% of total sentences) is **3.617%**. WER for Common Voice test set is **9.914%** directly and **7.77%** with a 4-gram language model.
+
+When using this model, make sure that your speech input is sampled at 16kHz.
+
+## Training
+This model has additionally pretrained on 3500h of a mix of Swedish local radio broadcasts, audio books and other audio sources. It has been fine-tuned for 120000 updates on NST + CommonVoice and then for an additional 20000 updates on CommonVoice only. The additional fine-tuning on CommonVoice hurts performance on the NST+CommonVoice test set somewhat and, unsurprisingly, improves it on the CommonVoice test set. It seems to perform generally better though [citation needed].
+
+![WER during training](chart_1.svg "WER")
+
+## Usage
+The model can be used directly (without a language model) as follows:
+```python
+import torch
+import torchaudio
+from datasets import load_dataset
+from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
+test_dataset = load_dataset("common_voice", "sv-SE", split="test[:2%]").
+processor = Wav2Vec2Processor.from_pretrained("KBLab/wav2vec2-large-voxrex-swedish")
+model = Wav2Vec2ForCTC.from_pretrained("KBLab/wav2vec2-large-voxpopuli-sv-swedish")
+resampler = torchaudio.transforms.Resample(48_000, 16_000)
+# Preprocessing the datasets.
+# We need to read the aduio files as arrays
+def speech_file_to_array_fn(batch):
+    speech_array, sampling_rate = torchaudio.load(batch["path"])
+    batch["speech"] = resampler(speech_array).squeeze().numpy()
+    return batch
+test_dataset = test_dataset.map(speech_file_to_array_fn)
+inputs = processor(test_dataset["speech"][:2], sampling_rate=16_000, return_tensors="pt", padding=True)
+with torch.no_grad():
+    logits = model(inputs.input_values, attention_mask=inputs.attention_mask).logits
+predicted_ids = torch.argmax(logits, dim=-1)
+print("Prediction:", processor.batch_decode(predicted_ids))
+print("Reference:", test_dataset["sentence"][:2])
+```
+

tokenizer_config.json

@@ -1 +1 @@
-{"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "<pad>", "do_lower_case": false, "word_delimiter_token": "|", "tokenizer_class": "Wav2Vec2CTCTokenizer"}
+{"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "<pad>", "do_lower_case": true, "word_delimiter_token": "|", "tokenizer_class": "Wav2Vec2CTCTokenizer"}

vocab.json

@@ -1 +1 @@
-{"<s>": 0, "<pad>": 1, "</s>": 2, "<unk>": 3, "|": 4, "T": 5, "E": 6, "A": 7, "N": 8, "R": 9, "S": 10, "I": 11, "L": 12, "D": 13, "O": 14, "M": 15, "K": 16, "G": 17, "U": 18, "V": 19, "F": 20, "H": 21, "Ä": 22, "Å": 23, "P": 24, "Ö": 25, "B": 26, "J": 27, "C": 28, "Y": 29, "X": 30, "W": 31, "Z": 32, "É": 33, "Q": 34, "8": 35, "2": 36, "5": 37, "9": 38, "1": 39, "6": 40, "7": 41, "3": 42, "4": 43, "0": 44, "'": 45}
+{"<pad>": 0, "<s>": 1, "</s>": 2, "<unk>": 3, "|": 4, "T": 5, "E": 6, "A": 7, "N": 8, "R": 9, "S": 10, "I": 11, "L": 12, "D": 13, "O": 14, "M": 15, "K": 16, "G": 17, "U": 18, "V": 19, "F": 20, "H": 21, "Ä": 22, "Å": 23, "P": 24, "Ö": 25, "B": 26, "J": 27, "C": 28, "Y": 29, "X": 30, "W": 31, "Z": 32, "É": 33, "Q": 34, "8": 35, "2": 36, "5": 37, "9": 38, "1": 39, "6": 40, "7": 41, "3": 42, "4": 43, "0": 44, "'": 45}