初始化项目，由ModelHub XC社区提供模型

Model: GetmanY1/wav2vec2-large-fi-150k-finetuned
Source: Original Platform

.gitattributes

@@ -0,0 +1,35 @@
+*.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
+*.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

README.md

@@ -0,0 +1,170 @@
+---
+license: apache-2.0
+tags:
+- automatic-speech-recognition
+- fi
+- finnish
+library_name: transformers
+language: fi
+base_model:
+- GetmanY1/wav2vec2-large-fi-150k
+model-index:
+  - name: wav2vec2-large-fi-150k-finetuned
+    results:
+      - task:
+          name: Automatic Speech Recognition
+          type: automatic-speech-recognition
+        dataset:
+          name: Lahjoita puhetta (Donate Speech)
+          type: lahjoita-puhetta
+          args: fi
+        metrics:
+          - name: Dev WER
+            type: wer
+            value: 15.34
+          - name: Dev CER
+            type: cer
+            value: 4.14
+          - name: Test WER
+            type: wer
+            value: 16.86
+          - name: Test CER
+            type: cer
+            value: 5.07
+      - task:
+          name: Automatic Speech Recognition
+          type: automatic-speech-recognition
+        dataset:
+          name: Finnish Parliament
+          type: FinParl
+          args: fi
+        metrics:
+          - name: Dev16 WER
+            type: wer
+            value: 11.3
+          - name: Dev16 CER
+            type: cer
+            value: 4.75
+          - name: Test16 WER
+            type: wer
+            value: 8.29
+          - name: Test16 CER
+            type: cer
+            value: 3.34
+          - name: Test20 WER
+            type: wer
+            value: 6.94
+          - name: Test20 CER
+            type: cer
+            value: 2.15
+      - task:
+          name: Automatic Speech Recognition
+          type: automatic-speech-recognition
+        dataset:
+          name: Common Voice 16.1
+          type: mozilla-foundation/common_voice_16_1
+          args: fi
+        metrics:
+        - name: Dev WER
+          type: wer
+          value: 7.17
+        - name: Dev CER
+          type: cer
+          value: 1.11
+        - name: Test WER
+          type: wer
+          value: 5.86
+        - name: Test CER
+          type: cer
+          value: 0.91
+      - task:
+          name: Automatic Speech Recognition
+          type: automatic-speech-recognition
+        dataset:
+          name: FLEURS
+          type: google/fleurs
+          args: fi_fi
+        metrics:
+        - name: Dev WER
+          type: wer
+          value: 9.2
+        - name: Dev CER
+          type: cer
+          value: 5.23
+        - name: Test WER
+          type: wer
+          value: 10.69
+        - name: Test CER
+          type: cer
+          value: 5.79
+---
+
+# Finnish Wav2vec2-Large ASR
+
+[GetmanY1/wav2vec2-large-fi-150k](https://huggingface.co/GetmanY1/wav2vec2-large-fi-150k) fine-tuned on 4600 hours of Finnish speech on 16kHz sampled speech audio:
+* 1500 hours of [Lahjoita puhetta (Donate Speech)](https://link.springer.com/article/10.1007/s10579-022-09606-3) (colloquial Finnish)
+* 3100 hours of the [Finnish Parliament dataset](https://link.springer.com/article/10.1007/s10579-023-09650-7)
+
+When using the model make sure that your speech input is also sampled at 16Khz.
+
+## Model description
+
+The Finnish Wav2Vec2 Large has the same architecture and uses the same training objective as the English and multilingual one described in [Paper](https://arxiv.org/abs/2006.11477).
+
+[GetmanY1/wav2vec2-large-fi-150k](https://huggingface.co/GetmanY1/wav2vec2-large-fi-150k) is a large-scale, 317-million parameter monolingual model pre-trained on 158k hours of unlabeled Finnish speech, including [KAVI radio and television archive materials](https://kavi.fi/en/radio-ja-televisioarkistointia-vuodesta-2008/), Lahjoita puhetta (Donate Speech), Finnish Parliament, Finnish VoxPopuli.
+
+You can read more about the pre-trained model from [this paper](https://www.isca-archive.org/interspeech_2025/getman25_interspeech.html). The training scripts are available on [GitHub](https://github.com/aalto-speech/large-scale-monolingual-speech-foundation-models).
+
+## Intended uses
+
+You can use this model for Finnish ASR (speech-to-text). 
+
+### How to use
+
+To transcribe audio files the model can be used as a standalone acoustic model as follows:
+
+```
+from transformers import Wav2Vec2Processor, Wav2Vec2ForCTC
+from datasets import load_dataset
+import torch
+
+# load model and processor
+processor = Wav2Vec2Processor.from_pretrained("GetmanY1/wav2vec2-large-fi-150k-finetuned")
+model = Wav2Vec2ForCTC.from_pretrained("GetmanY1/wav2vec2-large-fi-150k-finetuned")
+
+# load dummy dataset and read soundfiles
+ds = load_dataset("mozilla-foundation/common_voice_16_1", "fi", split='test')
+
+# tokenize
+input_values = processor(ds[0]["audio"]["array"], return_tensors="pt", padding="longest").input_values  # Batch size 1
+
+# retrieve logits
+logits = model(input_values).logits
+
+# take argmax and decode
+predicted_ids = torch.argmax(logits, dim=-1)
+transcription = processor.batch_decode(predicted_ids)
+```
+
+## Citation
+
+If you use our models or scripts, please cite our article as:
+
+```bibtex
+@inproceedings{getman25_interspeech,
+  title     = {{Is your model big enough? Training and interpreting large-scale monolingual speech foundation models}},
+  author    = {{Yaroslav Getman and Tamás Grósz and Tommi Lehtonen and Mikko Kurimo}},
+  year      = {{2025}},
+  booktitle = {{Interspeech 2025}},
+  pages     = {{231--235}},
+  doi       = {{10.21437/Interspeech.2025-46}},
+  issn      = {{2958-1796}},
+}
+```
+
+## Team Members
+
+- Yaroslav Getman, [Hugging Face profile](https://huggingface.co/GetmanY1), [LinkedIn profile](https://www.linkedin.com/in/yaroslav-getman/)
+- Tamas Grosz, [Hugging Face profile](https://huggingface.co/Grosy), [LinkedIn profile](https://www.linkedin.com/in/tam%C3%A1s-gr%C3%B3sz-950a049a/)
+
+Feel free to contact us for more details 🤗

config.json

@@ -0,0 +1,115 @@
+{
+  "activation_dropout": 0.0,
+  "adapter_attn_dim": null,
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": false,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForCTC"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 1,
+  "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": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_dropout": 0.0,
+  "feat_extract_norm": "layer",
+  "feat_proj_dropout": 0.1,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.0,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.1,
+  "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_min_masks": 0,
+  "mask_feature_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_min_masks": 2,
+  "mask_time_min_space": 1,
+  "mask_time_other": 0.0,
+  "mask_time_prob": 0.075,
+  "mask_time_selection": "static",
+  "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": 0,
+  "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": "4.36.0.dev0",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 34,
+  "xvector_output_dim": 512
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5633b8a5321d4813536e03bdac02bac5b9c188d10d50565dc2f6a903b6c8862e
+size 1261946832

preprocessor_config.json

@@ -0,0 +1,10 @@
+{
+  "do_normalize": true,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0,
+  "processor_class": "Wav2Vec2Processor",
+  "return_attention_mask": true,
+  "sampling_rate": 16000
+}

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,48 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "processor_class": "Wav2Vec2Processor",
+  "replace_word_delimiter_char": " ",
+  "target_lang": null,
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "<unk>",
+  "word_delimiter_token": "|"
+}

vocab.json

@@ -0,0 +1,36 @@
+{
+  "</s>": 2,
+  "<pad>": 0,
+  "<s>": 1,
+  "<unk>": 3,
+  "a": 16,
+  "b": 27,
+  "c": 28,
+  "d": 23,
+  "e": 19,
+  "f": 26,
+  "g": 25,
+  "h": 8,
+  "i": 9,
+  "j": 11,
+  "k": 21,
+  "l": 20,
+  "m": 18,
+  "n": 10,
+  "o": 7,
+  "p": 15,
+  "q": 31,
+  "r": 22,
+  "s": 17,
+  "t": 14,
+  "u": 6,
+  "v": 5,
+  "w": 30,
+  "x": 32,
+  "y": 13,
+  "z": 29,
+  "|": 4,
+  "ä": 12,
+  "å": 33,
+  "ö": 24
+}