End of training

README.md

@@ -1,199 +1,130 @@
 ---
 library_name: transformers
-tags: []
+license: cc-by-nc-4.0
+base_model: facebook/mms-1b-all
+tags:
+- generated_from_trainer
+metrics:
+- wer
+model-index:
+- name: ssc-koo-mms-model-mix-adapt-max3-devtrain
+  results: []
 ---
 
-# Model Card for Model ID
-
-<!-- Provide a quick summary of what the model is/does. -->
-
-
-
-## Model Details
-
-### Model Description
-
-<!-- Provide a longer summary of what this model is. -->
-
-This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
-
-- **Developed by:** [More Information Needed]
-- **Funded by [optional]:** [More Information Needed]
-- **Shared by [optional]:** [More Information Needed]
-- **Model type:** [More Information Needed]
-- **Language(s) (NLP):** [More Information Needed]
-- **License:** [More Information Needed]
-- **Finetuned from model [optional]:** [More Information Needed]
-
-### Model Sources [optional]
-
-<!-- Provide the basic links for the model. -->
-
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
-
-## Uses
-
-<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
-
-### Direct Use
-
-<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
-
-[More Information Needed]
-
-### Downstream Use [optional]
-
-<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
-
-[More Information Needed]
-
-### Out-of-Scope Use
-
-<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
-
-[More Information Needed]
-
-## Bias, Risks, and Limitations
-
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
-
-[More Information Needed]
-
-### Recommendations
-
-<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
-
-Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
-
-## How to Get Started with the Model
-
-Use the code below to get started with the model.
-
-[More Information Needed]
-
-## Training Details
-
-### Training Data
-
-<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
-
-[More Information Needed]
-
-### Training Procedure
-
-<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
-
-#### Preprocessing [optional]
-
-[More Information Needed]
-
-
-#### Training Hyperparameters
-
-- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
-
-#### Speeds, Sizes, Times [optional]
-
-<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
-
-[More Information Needed]
-
-## Evaluation
-
-<!-- This section describes the evaluation protocols and provides the results. -->
-
-### Testing Data, Factors & Metrics
-
-#### Testing Data
-
-<!-- This should link to a Dataset Card if possible. -->
-
-[More Information Needed]
-
-#### Factors
-
-<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
-
-[More Information Needed]
-
-#### Metrics
-
-<!-- These are the evaluation metrics being used, ideally with a description of why. -->
-
-[More Information Needed]
-
-### Results
-
-[More Information Needed]
-
-#### Summary
-
-
-
-## Model Examination [optional]
-
-<!-- Relevant interpretability work for the model goes here -->
-
-[More Information Needed]
-
-## Environmental Impact
-
-<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
-
-Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
-
-- **Hardware Type:** [More Information Needed]
-- **Hours used:** [More Information Needed]
-- **Cloud Provider:** [More Information Needed]
-- **Compute Region:** [More Information Needed]
-- **Carbon Emitted:** [More Information Needed]
-
-## Technical Specifications [optional]
-
-### Model Architecture and Objective
-
-[More Information Needed]
-
-### Compute Infrastructure
-
-[More Information Needed]
-
-#### Hardware
-
-[More Information Needed]
-
-#### Software
-
-[More Information Needed]
-
-## Citation [optional]
-
-<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
-
-**BibTeX:**
-
-[More Information Needed]
-
-**APA:**
-
-[More Information Needed]
-
-## Glossary [optional]
-
-<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
-
-[More Information Needed]
-
-## More Information [optional]
-
-[More Information Needed]
-
-## Model Card Authors [optional]
-
-[More Information Needed]
-
-## Model Card Contact
-
-[More Information Needed]
+<!-- 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. -->
+
+# ssc-koo-mms-model-mix-adapt-max3-devtrain
+
+This model is a fine-tuned version of [facebook/mms-1b-all](https://huggingface.co/facebook/mms-1b-all) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.5763
+- Cer: 0.1680
+- Wer: 0.6451
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0005
+- train_batch_size: 8
+- eval_batch_size: 6
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 16
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 100
+- num_epochs: 20
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch   | Step  | Validation Loss | Cer    | Wer    |
+|:-------------:|:-------:|:-----:|:---------------:|:------:|:------:|
+| 1.5137        | 0.3046  | 200   | 1.0743          | 0.2808 | 0.8787 |
+| 1.1278        | 0.6093  | 400   | 0.9499          | 0.2464 | 0.8133 |
+| 1.1259        | 0.9139  | 600   | 0.9075          | 0.2356 | 0.7980 |
+| 1.0472        | 1.2178  | 800   | 0.8841          | 0.2379 | 0.8012 |
+| 1.0557        | 1.5225  | 1000  | 0.8607          | 0.2349 | 0.7847 |
+| 1.0558        | 1.8271  | 1200  | 0.8432          | 0.2302 | 0.7773 |
+| 0.9952        | 2.1310  | 1400  | 0.8185          | 0.2240 | 0.7584 |
+| 0.9826        | 2.4356  | 1600  | 0.8156          | 0.2199 | 0.7607 |
+| 0.9879        | 2.7403  | 1800  | 0.8231          | 0.2163 | 0.7497 |
+| 0.9952        | 3.0442  | 2000  | 0.7887          | 0.2183 | 0.7505 |
+| 0.9306        | 3.3488  | 2200  | 0.7941          | 0.2159 | 0.7387 |
+| 0.9802        | 3.6535  | 2400  | 0.7656          | 0.2130 | 0.7454 |
+| 1.0176        | 3.9581  | 2600  | 0.7604          | 0.2084 | 0.7261 |
+| 0.9297        | 4.2620  | 2800  | 0.7790          | 0.2086 | 0.7406 |
+| 0.9436        | 4.5666  | 3000  | 0.7517          | 0.2095 | 0.7408 |
+| 0.9693        | 4.8713  | 3200  | 0.7559          | 0.2249 | 0.7452 |
+| 0.8687        | 5.1752  | 3400  | 0.7327          | 0.2084 | 0.7353 |
+| 0.8501        | 5.4798  | 3600  | 0.7505          | 0.2054 | 0.7499 |
+| 0.9161        | 5.7845  | 3800  | 0.7379          | 0.1997 | 0.7166 |
+| 0.9541        | 6.0883  | 4000  | 0.7210          | 0.2073 | 0.7348 |
+| 0.8721        | 6.3930  | 4200  | 0.7261          | 0.2002 | 0.7117 |
+| 0.9356        | 6.6976  | 4400  | 0.6904          | 0.1949 | 0.7011 |
+| 0.8998        | 7.0015  | 4600  | 0.6905          | 0.1952 | 0.7073 |
+| 0.8969        | 7.3062  | 4800  | 0.6716          | 0.1914 | 0.7017 |
+| 0.8693        | 7.6108  | 5000  | 0.6736          | 0.1917 | 0.7019 |
+| 0.8978        | 7.9155  | 5200  | 0.6847          | 0.1916 | 0.7026 |
+| 0.8343        | 8.2193  | 5400  | 0.6828          | 0.1960 | 0.7140 |
+| 0.8527        | 8.5240  | 5600  | 0.6751          | 0.1939 | 0.7075 |
+| 0.8032        | 8.8286  | 5800  | 0.6568          | 0.1918 | 0.6903 |
+| 0.8541        | 9.1325  | 6000  | 0.6982          | 0.1969 | 0.7172 |
+| 0.8209        | 9.4372  | 6200  | 0.6421          | 0.1860 | 0.6935 |
+| 0.7728        | 9.7418  | 6400  | 0.6418          | 0.1868 | 0.6886 |
+| 0.8137        | 10.0457 | 6600  | 0.6456          | 0.1860 | 0.6911 |
+| 0.7723        | 10.3503 | 6800  | 0.6398          | 0.1852 | 0.6852 |
+| 0.8187        | 10.6550 | 7000  | 0.6547          | 0.1855 | 0.6890 |
+| 0.7836        | 10.9596 | 7200  | 0.6367          | 0.1833 | 0.6860 |
+| 0.7864        | 11.2635 | 7400  | 0.6448          | 0.1841 | 0.6837 |
+| 0.8003        | 11.5682 | 7600  | 0.6299          | 0.1807 | 0.6854 |
+| 0.7817        | 11.8728 | 7800  | 0.6245          | 0.1855 | 0.6884 |
+| 0.7387        | 12.1767 | 8000  | 0.6154          | 0.1817 | 0.6776 |
+| 0.7685        | 12.4813 | 8200  | 0.6330          | 0.1804 | 0.6788 |
+| 0.7789        | 12.7860 | 8400  | 0.6076          | 0.1774 | 0.6580 |
+| 0.731         | 13.0899 | 8600  | 0.6056          | 0.1768 | 0.6633 |
+| 0.7256        | 13.3945 | 8800  | 0.6119          | 0.1779 | 0.6729 |
+| 0.707         | 13.6992 | 9000  | 0.6169          | 0.1787 | 0.6678 |
+| 0.7594        | 14.0030 | 9200  | 0.6089          | 0.1762 | 0.6578 |
+| 0.7542        | 14.3077 | 9400  | 0.6126          | 0.1787 | 0.6703 |
+| 0.7337        | 14.6123 | 9600  | 0.5991          | 0.1765 | 0.6697 |
+| 0.7228        | 14.9170 | 9800  | 0.5952          | 0.1730 | 0.6674 |
+| 0.7603        | 15.2209 | 10000 | 0.6016          | 0.1763 | 0.6648 |
+| 0.7238        | 15.5255 | 10200 | 0.5947          | 0.1749 | 0.6599 |
+| 0.7145        | 15.8302 | 10400 | 0.5934          | 0.1718 | 0.6538 |
+| 0.6758        | 16.1340 | 10600 | 0.5881          | 0.1732 | 0.6648 |
+| 0.7091        | 16.4387 | 10800 | 0.5985          | 0.1723 | 0.6617 |
+| 0.7195        | 16.7433 | 11000 | 0.5846          | 0.1700 | 0.6512 |
+| 0.6882        | 17.0472 | 11200 | 0.5884          | 0.1717 | 0.6534 |
+| 0.702         | 17.3519 | 11400 | 0.5869          | 0.1699 | 0.6495 |
+| 0.7373        | 17.6565 | 11600 | 0.5819          | 0.1706 | 0.6540 |
+| 0.6971        | 17.9612 | 11800 | 0.5768          | 0.1699 | 0.6534 |
+| 0.6595        | 18.2650 | 12000 | 0.5801          | 0.1686 | 0.6519 |
+| 0.7114        | 18.5697 | 12200 | 0.5814          | 0.1692 | 0.6502 |
+| 0.6836        | 18.8743 | 12400 | 0.5790          | 0.1684 | 0.6472 |
+| 0.6843        | 19.1782 | 12600 | 0.5782          | 0.1674 | 0.6453 |
+| 0.6761        | 19.4829 | 12800 | 0.5768          | 0.1683 | 0.6457 |
+| 0.6896        | 19.7875 | 13000 | 0.5763          | 0.1680 | 0.6451 |
+
+
+### Framework versions
+
+- Transformers 4.52.1
+- Pytorch 2.9.1+cu128
+- Datasets 3.6.0
+- Tokenizers 0.21.4

adapter.koo.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1262fd265a1f6a3e309db992ecdd1381172b0a9b95a86422fd731915cbd2415a
+size 9008632

config.json

@@ -0,0 +1,107 @@
+{
+  "activation_dropout": 0.05,
+  "adapter_attn_dim": 16,
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": false,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForCTC"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "codevector_dim": 1024,
+  "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": 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": 0.0,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.05,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.0,
+  "hidden_size": 1280,
+  "initializer_range": 0.02,
+  "intermediate_size": 5120,
+  "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": 0.05,
+  "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": 48,
+  "num_negatives": 100,
+  "output_hidden_size": 1280,
+  "pad_token_id": 69,
+  "proj_codevector_dim": 1024,
+  "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": "4.52.1",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 72,
+  "xvector_output_dim": 512
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ee6a8278c89713778a0301799e11a67e6aaaffda6279841cb93ed7c68b47b14
+size 3859101008

preprocessor_config.json

@@ -0,0 +1,9 @@
+{
+  "do_normalize": true,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "return_attention_mask": true,
+  "sampling_rate": 16000
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8642486932b4dee4713b6425b9eed0f1c27d4389ff8382b780e385711459339e
+size 5969

vocab.json

@@ -1,74 +1 @@
-{
-  "koo": {
-    "'": 17,
-    "-": 43,
-    "...": 67,
-    "A": 7,
-    "B": 46,
-    "C": 2,
-    "E": 52,
-    "G": 24,
-    "H": 64,
-    "I": 5,
-    "K": 12,
-    "L": 10,
-    "M": 51,
-    "N": 45,
-    "O": 58,
-    "P": 1,
-    "R": 31,
-    "S": 18,
-    "T": 38,
-    "U": 61,
-    "V": 39,
-    "W": 27,
-    "Y": 41,
-    "[PAD]": 69,
-    "[UNK]": 68,
-    "a": 35,
-    "b": 29,
-    "bb": 44,
-    "c": 60,
-    "d": 37,
-    "e": 66,
-    "f": 0,
-    "g": 62,
-    "gh": 8,
-    "h": 32,
-    "i": 54,
-    "j": 28,
-    "jj": 50,
-    "k": 22,
-    "ky": 23,
-    "l": 21,
-    "m": 25,
-    "mb": 49,
-    "n": 48,
-    "nd": 9,
-    "ng": 30,
-    "ngy": 20,
-    "njj": 26,
-    "nt": 56,
-    "ny": 33,
-    "nz": 40,
-    "o": 53,
-    "p": 55,
-    "r": 42,
-    "s": 3,
-    "t": 36,
-    "th": 34,
-    "ts": 59,
-    "u": 47,
-    "v": 19,
-    "w": 4,
-    "x": 63,
-    "y": 6,
-    "z": 14,
-    "|": 15,
-    "à": 13,
-    "ì": 16,
-    "í": 57,
-    "ù": 11,
-    "ķ": 65
-  }
-}
+{"koo": {"f": 0, "P": 1, "C": 2, "s": 3, "w": 4, "I": 5, "y": 6, "A": 7, "gh": 8, "nd": 9, "L": 10, "\u00f9": 11, "K": 12, "\u00e0": 13, "z": 14, "\u00ec": 16, "'": 17, "S": 18, "v": 19, "ngy": 20, "l": 21, "k": 22, "ky": 23, "G": 24, "m": 25, "njj": 26, "W": 27, "j": 28, "b": 29, "ng": 30, "R": 31, "h": 32, "ny": 33, "th": 34, "a": 35, "t": 36, "d": 37, "T": 38, "V": 39, "nz": 40, "Y": 41, "r": 42, "-": 43, "bb": 44, "N": 45, "B": 46, "u": 47, "n": 48, "mb": 49, "jj": 50, "M": 51, "E": 52, "o": 53, "i": 54, "p": 55, "nt": 56, "\u00ed": 57, "O": 58, "ts": 59, "c": 60, "U": 61, "g": 62, "x": 63, "H": 64, "\u0137": 65, "e": 66, "|": 15, "...": 67, "[UNK]": 68, "[PAD]": 69}}