Initial commit

.gitattributes

@@ -1,27 +1,17 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
-*.bin filter=lfs diff=lfs merge=lfs -text
 *.bin.* filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
 *.h5 filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tar.gz filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
 *.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
 *.model filter=lfs diff=lfs merge=lfs -text
 *.msgpack filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
 *.pb filter=lfs diff=lfs merge=lfs -text
 *.pt filter=lfs diff=lfs merge=lfs -text
 *.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text 
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.xz filter=lfs diff=lfs merge=lfs -text
-*.zip filter=lfs diff=lfs merge=lfs -text
-*.zstandard filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,74 @@
+---
+language: sv
+datasets:
+- common_voice
+- NST Swedish ASR Database
+- P4
+metrics:
+- wer
+tags:
+- audio
+- automatic-speech-recognition
+- speech
+license: cc0-1.0
+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 (C)
+
+**Disclaimer:** This is a work in progress. See [VoxRex](https://huggingface.co/KBLab/wav2vec2-large-voxrex) for more details.
+
+**Update 2022-01-10:** Updated to VoxRex-C version.
+
+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 **2.5%**. WER for Common Voice test set is **8.49%** directly and **7.37%** with a 4-gram language model.
+
+When using this model, make sure that your speech input is sampled at 16kHz.
+
+# Performance\*
+
+![Comparison](comparison.png "Comparison")
+<center><del>*<i>Chart shows performance without the additional 20k steps of Common Voice fine-tuning</i></del></center>
+
+## Training
+This model has been fine-tuned for 120000 updates on NST + CommonVoice<del> 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]</del>.
+
+![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-voxrex-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])
+```
+

alphabet.json

@@ -0,0 +1,3 @@
+{"labels": ["'", " ", "1", "A", "0", "Z", "S", "E", "K", "3", "Ö", "V", "H", "X", "Å", "M", "C", "8", "R", "J", "I", "5", "6", "U", "P", "D", "Q", "N", "4", "2", "B", "W", "7", "", "G", "F", "T", "Ä", "L", "O", "Y", "É", "9", "a", "b", "c", "d", "e", "f", "g", "h", "i", "j", "k", "l", "m", "n", "o", "p", "q", "r", "s", "t", "u", "v", "w", "x", "y", "z", "\u00e4", "\u00e5", "\u00e9", "\u00f4", "\u00f6", "\u00fc", "\u2047", "", "<s>", "</s>"], "is_bpe": false}
+
+    

config.json

@@ -0,0 +1,83 @@
+{
+  "activation_dropout": 0.05,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForCTC"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 1,
+  "codevector_dim": 256,
+  "contrastive_logits_temperature": 0.1,
+  "conv_bias": true,
+  "conv_dim": [
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512
+  ],
+  "conv_kernel": [
+    10,
+    3,
+    3,
+    3,
+    3,
+    2,
+    2
+  ],
+  "conv_stride": [
+    5,
+    2,
+    2,
+    2,
+    2,
+    2,
+    2
+  ],
+  "ctc_loss_reduction": "mean",
+  "ctc_zero_infinity": true,
+  "diversity_loss_weight": 0.1,
+  "do_stable_layer_norm": true,
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_dropout": 0.0,
+  "feat_extract_norm": "layer",
+  "feat_proj_dropout": 0.05,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.0,
+  "gradient_checkpointing": true,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.05,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.05,
+  "mask_channel_length": 10,
+  "mask_channel_min_space": 1,
+  "mask_channel_other": 0.0,
+  "mask_channel_prob": 0.0,
+  "mask_channel_selection": "static",
+  "mask_feature_length": 10,
+  "mask_feature_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_min_space": 1,
+  "mask_time_other": 0.0,
+  "mask_time_prob": 0.05,
+  "mask_time_selection": "static",
+  "model_type": "wav2vec2",
+  "num_attention_heads": 16,
+  "num_codevector_groups": 2,
+  "num_codevectors_per_group": 320,
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 128,
+  "num_feat_extract_layers": 7,
+  "num_hidden_layers": 24,
+  "num_negatives": 100,
+  "pad_token_id": 0,
+  "proj_codevector_dim": 256,
+  "transformers_version": "4.8.2",
+  "vocab_size": 46
+}

language_model/5gram.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c803936922612f71cf0abdb37763c18d24624e36bfa4abac20187cc17b88541d
+size 1981380707

language_model/attrs.json

@@ -0,0 +1 @@
+{"alpha": 0.5, "beta": 1.5, "unk_score_offset": -10.0, "score_boundary": true}

lm.py

@@ -0,0 +1,29 @@
+from transformers import Wav2Vec2ProcessorWithLM
+import torchaudio
+
+import torch
+from datasets import load_dataset
+from transformers import AutoModelForCTC, AutoProcessor
+import torchaudio.functional as F
+
+# processor = Wav2Vec2ProcessorWithLM.from_pretrained(".")
+
+model_id = "."
+
+sample_iter = iter(load_dataset("mozilla-foundation/common_voice_7_0", "sv-SE", split="test", streaming=True, use_auth_token=True))
+
+sample = next(sample_iter)
+resampled_audio = F.resample(torch.tensor(sample["audio"]["array"]), 48_000, 16_000).numpy()
+
+model = AutoModelForCTC.from_pretrained(model_id)
+processor = AutoProcessor.from_pretrained(model_id)
+
+input_values = processor(resampled_audio, return_tensors="pt").input_values
+
+with torch.no_grad():
+    logits = model(input_values).logits
+    import pdb
+    pdb.set_trace()
+
+    transcription = processor.batch_decode(logits.numpy()).text
+    print(transcription)

preprocessor_config.json

@@ -0,0 +1,9 @@
+{
+  "do_normalize": true,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0,
+  "return_attention_mask": true,
+  "sampling_rate": 16000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7138b3f9c5700388ddbd8b08a194290529778aba95327e7445a621cbe24ef508
+size 1262106353

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>"}

tokenizer_config.json

@@ -0,0 +1,9 @@
+{
+   "bos_token" : "<s>",
+   "do_lower_case" : true,
+   "eos_token" : "</s>",
+   "pad_token" : "<pad>",
+   "tokenizer_class" : "Wav2Vec2CTCTokenizer",
+   "unk_token" : "<unk>",
+   "word_delimiter_token" : "|"
+}

vocab.json

@@ -0,0 +1 @@
+{"<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}