Duplicate from NbAiLab/whisper-large-v2-nob

Co-authored-by: Per <pere@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,34 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz 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
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl 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
+*.safetensors 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
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

README.md

@@ -0,0 +1,69 @@
+---
+language:
+- 'no'
+license: apache-2.0
+tags:
+- whisper-event
+- norwegian
+datasets:
+- NbAiLab/NCC_S
+- NbAiLab/NPSC
+- NbAiLab/NST
+metrics:
+- wer
+model-index:
+- name: Whisper Large Norwegian Bokmål
+  results:
+  - task:
+      name: Automatic Speech Recognition
+      type: automatic-speech-recognition
+    dataset:
+      name: FLEURS
+      type: google/fleurs
+      config: nb_no
+      split: validation
+      args: nb_no
+    metrics:
+    - name: Wer
+      type: wer
+      value: 10.718635559082031
+duplicated_from: NbAiLab/whisper-large-v2-nob
+---
+
+# Whisper Large Norwegian Bokmål
+
+This model is a fine-tuned version of [openai/whisper-large-v2](https://huggingface.co/openai/whisper-large-v2) trained on several datasets.
+
+It is currently in the middle of a large training. Currently it achieves the following results on the evaluation set:
+- Loss: 0.2477
+- Wer: 10.718635559082031
+
+## Model description
+
+The model is trained on a large corpus of roughly 5.000 hours of voice. The sources are subtitles from the Norwegian broadcaster NRK, transcribed speeches from the Norwegian parliament and voice recordings from Norsk Språkteknologi. 
+
+## Intended uses & limitations
+
+The model will be free for everyone to use when it is finished.
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 3e-06
+- train_batch_size: 64
+- gradient_accumulation_steps: 2
+- eval_batch_size: 32
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: constant with warmpu
+- lr_scheduler_warmup_steps: 1000
+- training_steps: 50.000 (currently @1.000)
+- mixed_precision_training: fp16
+- deepspeed: true
+
+### Live Training results
+See [Tensorboad Metrics](https://huggingface.co/NbAiLab/whisper-large-v2-nob/tensorboard)
+
+
+
+

added_tokens.json

@@ -0,0 +1,109 @@
+{
+  "<|af|>": 50327,
+  "<|am|>": 50334,
+  "<|ar|>": 50272,
+  "<|as|>": 50350,
+  "<|az|>": 50304,
+  "<|ba|>": 50355,
+  "<|be|>": 50330,
+  "<|bg|>": 50292,
+  "<|bn|>": 50302,
+  "<|bo|>": 50347,
+  "<|br|>": 50309,
+  "<|bs|>": 50315,
+  "<|ca|>": 50270,
+  "<|cs|>": 50283,
+  "<|cy|>": 50297,
+  "<|da|>": 50285,
+  "<|de|>": 50261,
+  "<|el|>": 50281,
+  "<|endoftext|>": 50257,
+  "<|en|>": 50259,
+  "<|es|>": 50262,
+  "<|et|>": 50307,
+  "<|eu|>": 50310,
+  "<|fa|>": 50300,
+  "<|fi|>": 50277,
+  "<|fo|>": 50338,
+  "<|fr|>": 50265,
+  "<|gl|>": 50319,
+  "<|gu|>": 50333,
+  "<|haw|>": 50352,
+  "<|ha|>": 50354,
+  "<|hi|>": 50276,
+  "<|hr|>": 50291,
+  "<|ht|>": 50339,
+  "<|hu|>": 50286,
+  "<|hy|>": 50312,
+  "<|id|>": 50275,
+  "<|is|>": 50311,
+  "<|it|>": 50274,
+  "<|iw|>": 50279,
+  "<|ja|>": 50266,
+  "<|jw|>": 50356,
+  "<|ka|>": 50329,
+  "<|kk|>": 50316,
+  "<|km|>": 50323,
+  "<|kn|>": 50306,
+  "<|ko|>": 50264,
+  "<|la|>": 50294,
+  "<|lb|>": 50345,
+  "<|ln|>": 50353,
+  "<|lo|>": 50336,
+  "<|lt|>": 50293,
+  "<|lv|>": 50301,
+  "<|mg|>": 50349,
+  "<|mi|>": 50295,
+  "<|mk|>": 50308,
+  "<|ml|>": 50296,
+  "<|mn|>": 50314,
+  "<|mr|>": 50320,
+  "<|ms|>": 50282,
+  "<|mt|>": 50343,
+  "<|my|>": 50346,
+  "<|ne|>": 50313,
+  "<|nl|>": 50271,
+  "<|nn|>": 50342,
+  "<|nocaptions|>": 50362,
+  "<|notimestamps|>": 50363,
+  "<|no|>": 50288,
+  "<|oc|>": 50328,
+  "<|pa|>": 50321,
+  "<|pl|>": 50269,
+  "<|ps|>": 50340,
+  "<|pt|>": 50267,
+  "<|ro|>": 50284,
+  "<|ru|>": 50263,
+  "<|sa|>": 50344,
+  "<|sd|>": 50332,
+  "<|si|>": 50322,
+  "<|sk|>": 50298,
+  "<|sl|>": 50305,
+  "<|sn|>": 50324,
+  "<|so|>": 50326,
+  "<|sq|>": 50317,
+  "<|sr|>": 50303,
+  "<|startoflm|>": 50360,
+  "<|startofprev|>": 50361,
+  "<|startoftranscript|>": 50258,
+  "<|su|>": 50357,
+  "<|sv|>": 50273,
+  "<|sw|>": 50318,
+  "<|ta|>": 50287,
+  "<|te|>": 50299,
+  "<|tg|>": 50331,
+  "<|th|>": 50289,
+  "<|tk|>": 50341,
+  "<|tl|>": 50348,
+  "<|transcribe|>": 50359,
+  "<|translate|>": 50358,
+  "<|tr|>": 50268,
+  "<|tt|>": 50351,
+  "<|uk|>": 50280,
+  "<|ur|>": 50290,
+  "<|uz|>": 50337,
+  "<|vi|>": 50278,
+  "<|yi|>": 50335,
+  "<|yo|>": 50325,
+  "<|zh|>": 50260
+}

config.json

@@ -0,0 +1,41 @@
+{
+  "_name_or_path": "openai/whisper-large-v2",
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "architectures": [
+    "WhisperForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "begin_suppress_tokens": [
+    220,
+    50257
+  ],
+  "bos_token_id": 50257,
+  "d_model": 1280,
+  "decoder_attention_heads": 20,
+  "decoder_ffn_dim": 5120,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 32,
+  "decoder_start_token_id": 50258,
+  "dropout": 0.0,
+  "encoder_attention_heads": 20,
+  "encoder_ffn_dim": 5120,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 32,
+  "eos_token_id": 50257,
+  "forced_decoder_ids": null,
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "max_length": 448,
+  "max_source_positions": 1500,
+  "max_target_positions": 448,
+  "model_type": "whisper",
+  "num_hidden_layers": 32,
+  "num_mel_bins": 80,
+  "pad_token_id": 50257,
+  "scale_embedding": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.26.0.dev0",
+  "use_cache": false,
+  "vocab_size": 51865
+}

ds_config.json

@@ -0,0 +1,48 @@
+{
+    "fp16": {
+        "enabled": "auto",
+        "loss_scale": 0,
+        "loss_scale_window": 1000,
+        "initial_scale_power": 16,
+        "hysteresis": 2,
+        "min_loss_scale": 1
+    },
+
+    "optimizer": {
+        "type": "AdamW",
+        "params": {
+            "lr": "auto",
+            "betas": "auto",
+            "eps": "auto",
+            "weight_decay": "auto"
+        }
+    },
+
+    "scheduler": {
+        "type": "WarmupLR",
+        "params": {
+            "warmup_min_lr": "auto",
+            "warmup_max_lr": "auto",
+            "warmup_num_steps": "auto"
+        }
+    },
+
+    "zero_optimization": {
+        "stage": 2,
+        "offload_optimizer": {
+            "device": "cpu",
+            "pin_memory": true
+        },
+        "allgather_partitions": true,
+        "allgather_bucket_size": 2e8,
+        "overlap_comm": true,
+        "reduce_scatter": true,
+        "reduce_bucket_size": 2e8,
+        "contiguous_gradients": true
+    },
+
+    "gradient_accumulation_steps": "auto",
+    "gradient_clipping": "auto",
+    "train_batch_size": "auto",
+    "train_micro_batch_size_per_gpu": "auto"
+}

normalizer.json

@@ -0,0 +1,1742 @@
+{
+  "accessorise": "accessorize",
+  "accessorised": "accessorized",
+  "accessorises": "accessorizes",
+  "accessorising": "accessorizing",
+  "acclimatisation": "acclimatization",
+  "acclimatise": "acclimatize",
+  "acclimatised": "acclimatized",
+  "acclimatises": "acclimatizes",
+  "acclimatising": "acclimatizing",
+  "accoutrements": "accouterments",
+  "aeon": "eon",
+  "aeons": "eons",
+  "aerogramme": "aerogram",
+  "aerogrammes": "aerograms",
+  "aeroplane": "airplane",
+  "aeroplanes": "airplanes",
+  "aesthete": "esthete",
+  "aesthetes": "esthetes",
+  "aesthetic": "esthetic",
+  "aesthetically": "esthetically",
+  "aesthetics": "esthetics",
+  "aetiology": "etiology",
+  "ageing": "aging",
+  "aggrandisement": "aggrandizement",
+  "agonise": "agonize",
+  "agonised": "agonized",
+  "agonises": "agonizes",
+  "agonising": "agonizing",
+  "agonisingly": "agonizingly",
+  "almanack": "almanac",
+  "almanacks": "almanacs",
+  "aluminium": "aluminum",
+  "amortisable": "amortizable",
+  "amortisation": "amortization",
+  "amortisations": "amortizations",
+  "amortise": "amortize",
+  "amortised": "amortized",
+  "amortises": "amortizes",
+  "amortising": "amortizing",
+  "amphitheatre": "amphitheater",
+  "amphitheatres": "amphitheaters",
+  "anaemia": "anemia",
+  "anaemic": "anemic",
+  "anaesthesia": "anesthesia",
+  "anaesthetic": "anesthetic",
+  "anaesthetics": "anesthetics",
+  "anaesthetise": "anesthetize",
+  "anaesthetised": "anesthetized",
+  "anaesthetises": "anesthetizes",
+  "anaesthetising": "anesthetizing",
+  "anaesthetist": "anesthetist",
+  "anaesthetists": "anesthetists",
+  "anaesthetize": "anesthetize",
+  "anaesthetized": "anesthetized",
+  "anaesthetizes": "anesthetizes",
+  "anaesthetizing": "anesthetizing",
+  "analogue": "analog",
+  "analogues": "analogs",
+  "analyse": "analyze",
+  "analysed": "analyzed",
+  "analyses": "analyzes",
+  "analysing": "analyzing",
+  "anglicise": "anglicize",
+  "anglicised": "anglicized",
+  "anglicises": "anglicizes",
+  "anglicising": "anglicizing",
+  "annualised": "annualized",
+  "antagonise": "antagonize",
+  "antagonised": "antagonized",
+  "antagonises": "antagonizes",
+  "antagonising": "antagonizing",
+  "apologise": "apologize",
+  "apologised": "apologized",
+  "apologises": "apologizes",
+  "apologising": "apologizing",
+  "appal": "appall",
+  "appals": "appalls",
+  "appetiser": "appetizer",
+  "appetisers": "appetizers",
+  "appetising": "appetizing",
+  "appetisingly": "appetizingly",
+  "arbour": "arbor",
+  "arbours": "arbors",
+  "archaeologically": "archeologically",
+  "archaeologist": "archeologist",
+  "archaeologists": "archeologists",
+  "archaeology": "archeology</span>",
+  "archeological": "archaeological",
+  "ardour": "ardor",
+  "armour": "armor",
+  "armoured": "armored",
+  "armourer": "armorer",
+  "armourers": "armorers",
+  "armouries": "armories",
+  "armoury": "armory",
+  "artefact": "artifact",
+  "artefacts": "artifacts",
+  "authorise": "authorize",
+  "authorised": "authorized",
+  "authorises": "authorizes",
+  "authorising": "authorizing",
+  "axe": "ax",
+  "backpedalled": "backpedaled",
+  "backpedalling": "backpedaling",
+  "bannister": "banister",
+  "bannisters": "banisters",
+  "baptise": "baptize",
+  "baptised": "baptized",
+  "baptises": "baptizes",
+  "baptising": "baptizing",
+  "bastardise": "bastardize",
+  "bastardised": "bastardized",
+  "bastardises": "bastardizes",
+  "bastardising": "bastardizing",
+  "battleax": "battleaxe",
+  "baulk": "balk",
+  "baulked": "balked",
+  "baulking": "balking",
+  "baulks": "balks",
+  "bedevilled": "bedeviled",
+  "bedevilling": "bedeviling",
+  "behaviour": "behavior",
+  "behavioural": "behavioral",
+  "behaviourism": "behaviorism",
+  "behaviourist": "behaviorist",
+  "behaviourists": "behaviorists",
+  "behaviours": "behaviors",
+  "behove": "behoove",
+  "behoved": "behooved",
+  "behoves": "behooves",
+  "bejewelled": "bejeweled",
+  "belabour": "belabor",
+  "belaboured": "belabored",
+  "belabouring": "belaboring",
+  "belabours": "belabors",
+  "bevelled": "beveled",
+  "bevvies": "bevies",
+  "bevvy": "bevy",
+  "biassed": "biased",
+  "biassing": "biasing",
+  "bingeing": "binging",
+  "bougainvillaea": "bougainvillea",
+  "bougainvillaeas": "bougainvilleas",
+  "bowdlerise": "bowdlerize",
+  "bowdlerised": "bowdlerized",
+  "bowdlerises": "bowdlerizes",
+  "bowdlerising": "bowdlerizing",
+  "breathalyse": "breathalyze",
+  "breathalysed": "breathalyzed",
+  "breathalyser": "breathalyzer",
+  "breathalysers": "breathalyzers",
+  "breathalyses": "breathalyzes",
+  "breathalysing": "breathalyzing",
+  "brutalise": "brutalize",
+  "brutalised": "brutalized",
+  "brutalises": "brutalizes",
+  "brutalising": "brutalizing",
+  "busses": "buses",
+  "bussing": "busing",
+  "caesarean": "cesarean",
+  "caesareans": "cesareans",
+  "calibre": "caliber",
+  "calibres": "calibers",
+  "calliper": "caliper",
+  "callipers": "calipers",
+  "callisthenics": "calisthenics",
+  "canalise": "canalize",
+  "canalised": "canalized",
+  "canalises": "canalizes",
+  "canalising": "canalizing",
+  "cancelation": "cancellation",
+  "cancelations": "cancellations",
+  "cancelled": "canceled",
+  "cancelling": "canceling",
+  "candour": "candor",
+  "cannibalise": "cannibalize",
+  "cannibalised": "cannibalized",
+  "cannibalises": "cannibalizes",
+  "cannibalising": "cannibalizing",
+  "canonise": "canonize",
+  "canonised": "canonized",
+  "canonises": "canonizes",
+  "canonising": "canonizing",
+  "capitalise": "capitalize",
+  "capitalised": "capitalized",
+  "capitalises": "capitalizes",
+  "capitalising": "capitalizing",
+  "caramelise": "caramelize",
+  "caramelised": "caramelized",
+  "caramelises": "caramelizes",
+  "caramelising": "caramelizing",
+  "carbonise": "carbonize",
+  "carbonised": "carbonized",
+  "carbonises": "carbonizes",
+  "carbonising": "carbonizing",
+  "carolled": "caroled",
+  "carolling": "caroling",
+  "catalogue": "catalog",
+  "catalogued": "cataloged",
+  "catalogues": "catalogs",
+  "cataloguing": "cataloging",
+  "catalyse": "catalyze",
+  "catalysed": "catalyzed",
+  "catalyses": "catalyzes",
+  "catalysing": "catalyzing",
+  "categorise": "categorize",
+  "categorised": "categorized",
+  "categorises": "categorizes",
+  "categorising": "categorizing",
+  "cauterise": "cauterize",
+  "cauterised": "cauterized",
+  "cauterises": "cauterizes",
+  "cauterising": "cauterizing",
+  "cavilled": "caviled",
+  "cavilling": "caviling",
+  "centigramme": "centigram",
+  "centigrammes": "centigrams",
+  "centilitre": "centiliter",
+  "centilitres": "centiliters",
+  "centimetre": "centimeter",
+  "centimetres": "centimeters",
+  "centralise": "centralize",
+  "centralised": "centralized",
+  "centralises": "centralizes",
+  "centralising": "centralizing",
+  "centre": "center",
+  "centred": "centered",
+  "centrefold": "centerfold",
+  "centrefolds": "centerfolds",
+  "centrepiece": "centerpiece",
+  "centrepieces": "centerpieces",
+  "centres": "centers",
+  "channelled": "channeled",
+