Merge branch 'main' of https://huggingface.co/RASMUS/wav2vec2-xlsr-fi-train-aug-lm-1B into main

README.md

@@ -1,11 +1,35 @@
 ---
+language: fi
+datasets:
+- mozilla-foundation/common_voice_7_0
+metrics:
+- wer
+- cer
 tags:
 - generated_from_trainer
+- mozilla-foundation/common_voice_7_0
+- audio
+- automatic-speech-recognition
+- speech
+- robust-speech-event
 model-index:
-- name: wav2vec2-xlsr-fi-train-aug-lm-1B
-  results: []
+- name: XLS-R 1B Wav2Vec2 Finnish by Rasmus Toivanen
+  results:
+  - task: 
+      name: Automatic Speech Recognition
+      type: automatic-speech-recognition
+    dataset:
+      name: Common Voice 7
+      type: mozilla-foundation/common_voice_7_0
+      args: fi
+    metrics:
+       - name: Test WER
+         type: wer
+         value: 10.96
+       - name: Test CER
+         type: cer
+         value: 2.81
 ---
-
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
 

alphabet.json

@@ -0,0 +1 @@
+{"labels": [" ", "'", "-", "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", "\u00f6", "\u2047", "", "<s>", "</s>"], "is_bpe": false}

language_model/attrs.json

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

language_model/kenlm_fi_model_correct.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14c745cf96cd5dc073bcd23e2968e4b5059af1154b4f4ee029725a136fd9a929
+size 16497522

preprocessor_config.json

@@ -5,5 +5,6 @@
   "padding_side": "right",
   "padding_value": 0.0,
   "return_attention_mask": true,
-  "sampling_rate": 16000
-}
+  "sampling_rate": 16000,
+  "processor_class": "Wav2Vec2ProcessorWithLM"
+}

special_tokens_map.json

@@ -1 +1 @@
-{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]", "additional_special_tokens": [{"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}]}
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]", "additional_special_tokens": [{"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}]}

tokenizer_config.json

@@ -1 +1 @@
-{"unk_token": "[UNK]", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "[PAD]", "do_lower_case": false, "word_delimiter_token": "|", "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "./", "tokenizer_class": "Wav2Vec2CTCTokenizer"}
+{"unk_token": "[UNK]", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "[PAD]", "do_lower_case": false, "word_delimiter_token": "|", "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "RASMUS/wav2vec2-xlsr-fi-train-aug-lm-1B", "tokenizer_class": "Wav2Vec2CTCTokenizer"}