初始化项目，由ModelHub XC社区提供模型

Model: saattrupdan/wav2vec2-xls-r-300m-ftspeech
Source: Original Platform

.gitattributes

@@ -0,0 +1,28 @@
+*.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
+*.h5 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
+model.safetensors filter=lfs diff=lfs merge=lfs -text

.gitignore

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

README.md

@@ -0,0 +1,53 @@
+---
+language:
+- da
+license: other
+datasets:
+- ftspeech
+metrics:
+- wer
+tasks:
+- automatic-speech-recognition
+base_model: facebook/wav2vec2-xls-r-300m
+model-index:
+- name: wav2vec2-xls-r-300m-ftspeech
+  results:
+  - task:
+      type: automatic-speech-recognition
+    dataset:
+      name: Danish Common Voice 8.0
+      type: mozilla-foundation/common_voice_8_0
+      args: da
+    metrics:
+    - type: wer
+      value: 17.91
+  - task:
+      type: automatic-speech-recognition
+    dataset:
+      name: Alvenir ASR test dataset
+      type: Alvenir/alvenir_asr_da_eval
+    metrics:
+    - type: wer
+      value: 13.84
+---
+
+# XLS-R-300m-FTSpeech
+
+## Model description
+
+This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the [FTSpeech dataset](https://ftspeech.github.io/), being a dataset of 1,800 hours of transcribed speeches from the Danish parliament.
+
+
+## Performance
+
+The model achieves the following WER scores (lower is better):
+
+| **Dataset** | **WER without LM** | **WER with 5-gram LM** |
+| :---:   | ---: | ---: |
+| [Danish part of Common Voice 8.0](https://huggingface.co/datasets/mozilla-foundation/common_voice_8_0/viewer/da/train) | 20.48 | 17.91 |
+| [Alvenir test set](https://huggingface.co/datasets/Alvenir/alvenir_asr_da_eval) | 15.46 | 13.84 |
+
+
+## License
+
+The use of this model needs to adhere to [this license from the Danish Parliament](https://www.ft.dk/da/aktuelt/tv-fra-folketinget/deling-og-rettigheder).

alphabet.json

@@ -0,0 +1 @@
+{"labels": ["u", "t", "d", "i", " ", "r", "b", "v", "h", "\u00e6", "z", "a", "e", "l", "f", "k", "y", "w", "g", "\u00f8", "p", "s", "c", "\u00e5", "j", "x", "\u00e9", "n", "q", "m", "o", "\u2047", "", "<s>", "</s>"], "is_bpe": false}

config.json

@@ -0,0 +1,108 @@
+{
+  "_name_or_path": "facebook/wav2vec2-xls-r-300m",
+  "activation_dropout": 0.0,
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": false,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForCTC"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 33,
+  "classifier_proj_size": 256,
+  "codevector_dim": 768,
+  "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": "sum",
+  "ctc_zero_infinity": false,
+  "diversity_loss_weight": 0.1,
+  "do_stable_layer_norm": true,
+  "eos_token_id": 34,
+  "feat_extract_activation": "gelu",
+  "feat_extract_dropout": 0.0,
+  "feat_extract_norm": "layer",
+  "feat_proj_dropout": 0.0,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.0,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.0,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.0,
+  "mask_feature_length": 10,
+  "mask_feature_min_masks": 0,
+  "mask_feature_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_min_masks": 2,
+  "mask_time_prob": 0.075,
+  "model_type": "wav2vec2",
+  "num_adapter_layers": 3,
+  "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,
+  "output_hidden_size": 1024,
+  "pad_token_id": 32,
+  "proj_codevector_dim": 768,
+  "tdnn_dilation": [
+    1,
+    2,
+    3,
+    1,
+    1
+  ],
+  "tdnn_dim": [
+    512,
+    512,
+    512,
+    512,
+    1500
+  ],
+  "tdnn_kernel": [
+    5,
+    3,
+    3,
+    1,
+    1
+  ],
+  "torch_dtype": "float32",
+  "transformers_version": "4.16.2",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 35,
+  "xvector_output_dim": 512
+}

language_model/5gram.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5ea8c4a370997de831c485a8993503c000710c9b1ff61b4d78b25f5140ce77d
+size 1253607665

language_model/attrs.json

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

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2d42bb9c2db3a576d2a2c75c7b9080f1195f9acffe255317694e8c5b8143ca3
+size 1261950932

preprocessor_config.json

@@ -0,0 +1,10 @@
+{
+  "do_normalize": true,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "processor_class": "Wav2Vec2ProcessorWithLM",
+  "return_attention_mask": true,
+  "sampling_rate": 16000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a748eb6321c628711e3fdcbbecc3517727e4eaf17c12d0d5f32e12a0cec166ff
+size 1262067185

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 @@
+{"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": "saattrupdan/wav2vec2-xls-r-300m-ftspeech", "processor_class": "Wav2Vec2ProcessorWithLM", "tokenizer_class": "Wav2Vec2CTCTokenizer"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ccf149ef4f0e244a19863e7355ce6c35368fc954d16739983a0672e85cea776
+size 3055

vocab.json

@@ -0,0 +1 @@
+{"u": 0, "t": 1, "d": 2, "i": 3, "|": 4, "r": 5, "b": 6, "v": 7, "h": 8, "æ": 9, "z": 10, "a": 11, "e": 12, "l": 13, "f": 14, "k": 15, "y": 16, "w": 17, "g": 18, "ø": 19, "p": 20, "s": 21, "c": 22, "å": 23, "j": 24, "x": 25, "é": 26, "n": 27, "q": 28, "m": 29, "o": 30, "<unk>": 31, "<pad>": 32, "<s>": 33, "</s>": 34}