End of training

README.md

@@ -1,199 +1,134 @@
 ---
 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-bxk-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-bxk-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: 0.4177
+- Cer: 0.1145
+- Wer: 0.4635
+
+## 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    |
+|:-------------:|:-------:|:-----:|:---------------:|:------:|:------:|
+| 1.0152        | 0.2880  | 200   | 0.7453          | 0.1792 | 0.6636 |
+| 0.9038        | 0.5760  | 400   | 0.6654          | 0.1642 | 0.6124 |
+| 0.8634        | 0.8639  | 600   | 0.6451          | 0.1573 | 0.5944 |
+| 0.8008        | 1.1512  | 800   | 0.6181          | 0.1539 | 0.5788 |
+| 0.8145        | 1.4392  | 1000  | 0.5989          | 0.1500 | 0.5696 |
+| 0.7969        | 1.7271  | 1200  | 0.5997          | 0.1508 | 0.5660 |
+| 0.7078        | 2.0144  | 1400  | 0.5896          | 0.1481 | 0.5644 |
+| 0.7844        | 2.3024  | 1600  | 0.5802          | 0.1484 | 0.5630 |
+| 0.7457        | 2.5904  | 1800  | 0.5771          | 0.1442 | 0.5489 |
+| 0.7882        | 2.8783  | 2000  | 0.5700          | 0.1432 | 0.5473 |
+| 0.7065        | 3.1656  | 2200  | 0.5637          | 0.1423 | 0.5444 |
+| 0.7029        | 3.4536  | 2400  | 0.5553          | 0.1409 | 0.5411 |
+| 0.7347        | 3.7415  | 2600  | 0.5652          | 0.1406 | 0.5324 |
+| 0.7281        | 4.0288  | 2800  | 0.5459          | 0.1398 | 0.5379 |
+| 0.7065        | 4.3168  | 3000  | 0.5478          | 0.1418 | 0.5434 |
+| 0.6996        | 4.6048  | 3200  | 0.5494          | 0.1387 | 0.5354 |
+| 0.7333        | 4.8927  | 3400  | 0.5412          | 0.1391 | 0.5363 |
+| 0.6437        | 5.1800  | 3600  | 0.5324          | 0.1379 | 0.5221 |
+| 0.7171        | 5.4680  | 3800  | 0.5292          | 0.1361 | 0.5182 |
+| 0.7055        | 5.7559  | 4000  | 0.5265          | 0.1365 | 0.5218 |
+| 0.6608        | 6.0432  | 4200  | 0.5306          | 0.1358 | 0.5214 |
+| 0.6704        | 6.3312  | 4400  | 0.5358          | 0.1351 | 0.5189 |
+| 0.6623        | 6.6192  | 4600  | 0.5188          | 0.1359 | 0.5198 |
+| 0.689         | 6.9071  | 4800  | 0.5230          | 0.1361 | 0.5225 |
+| 0.668         | 7.1944  | 5000  | 0.5113          | 0.1325 | 0.5119 |
+| 0.6516        | 7.4824  | 5200  | 0.5126          | 0.1329 | 0.5108 |
+| 0.6597        | 7.7703  | 5400  | 0.5140          | 0.1315 | 0.5097 |
+| 0.6099        | 8.0576  | 5600  | 0.5126          | 0.1317 | 0.5057 |
+| 0.6827        | 8.3456  | 5800  | 0.5238          | 0.1308 | 0.5030 |
+| 0.6976        | 8.6335  | 6000  | 0.5031          | 0.1300 | 0.5078 |
+| 0.6143        | 8.9215  | 6200  | 0.4909          | 0.1322 | 0.5124 |
+| 0.6143        | 9.2088  | 6400  | 0.5019          | 0.1304 | 0.5110 |
+| 0.6136        | 9.4968  | 6600  | 0.5229          | 0.1290 | 0.4968 |
+| 0.6299        | 9.7847  | 6800  | 0.5080          | 0.1303 | 0.5021 |
+| 0.6343        | 10.0720 | 7000  | 0.4889          | 0.1309 | 0.5062 |
+| 0.6035        | 10.3600 | 7200  | 0.4830          | 0.1302 | 0.5087 |
+| 0.656         | 10.6479 | 7400  | 0.4803          | 0.1276 | 0.4936 |
+| 0.6167        | 10.9359 | 7600  | 0.4875          | 0.1271 | 0.4926 |
+| 0.6162        | 11.2232 | 7800  | 0.4712          | 0.1262 | 0.4890 |
+| 0.5932        | 11.5112 | 8000  | 0.4712          | 0.1261 | 0.4913 |
+| 0.6125        | 11.7991 | 8200  | 0.4654          | 0.1274 | 0.5007 |
+| 0.5689        | 12.0864 | 8400  | 0.4684          | 0.1247 | 0.4851 |
+| 0.5888        | 12.3744 | 8600  | 0.4635          | 0.1242 | 0.4816 |
+| 0.61          | 12.6623 | 8800  | 0.4563          | 0.1236 | 0.4828 |
+| 0.588         | 12.9503 | 9000  | 0.4517          | 0.1234 | 0.4857 |
+| 0.6083        | 13.2376 | 9200  | 0.4457          | 0.1228 | 0.4873 |
+| 0.5668        | 13.5256 | 9400  | 0.4483          | 0.1214 | 0.4784 |
+| 0.5896        | 13.8135 | 9600  | 0.4472          | 0.1209 | 0.4759 |
+| 0.5564        | 14.1008 | 9800  | 0.4411          | 0.1222 | 0.4819 |
+| 0.5921        | 14.3888 | 10000 | 0.4425          | 0.1205 | 0.4772 |
+| 0.6036        | 14.6767 | 10200 | 0.4410          | 0.1200 | 0.4756 |
+| 0.5923        | 14.9647 | 10400 | 0.4349          | 0.1198 | 0.4724 |
+| 0.5603        | 15.2520 | 10600 | 0.4357          | 0.1184 | 0.4694 |
+| 0.5548        | 15.5400 | 10800 | 0.4362          | 0.1196 | 0.4717 |
+| 0.5708        | 15.8279 | 11000 | 0.4334          | 0.1188 | 0.4757 |
+| 0.5575        | 16.1152 | 11200 | 0.4302          | 0.1178 | 0.4720 |
+| 0.5318        | 16.4032 | 11400 | 0.4299          | 0.1171 | 0.4697 |
+| 0.5593        | 16.6911 | 11600 | 0.4250          | 0.1155 | 0.4681 |
+| 0.5718        | 16.9791 | 11800 | 0.4248          | 0.1163 | 0.4692 |
+| 0.5748        | 17.2664 | 12000 | 0.4243          | 0.1154 | 0.4649 |
+| 0.5614        | 17.5544 | 12200 | 0.4232          | 0.1172 | 0.4727 |
+| 0.5359        | 17.8423 | 12400 | 0.4224          | 0.1149 | 0.4660 |
+| 0.5596        | 18.1296 | 12600 | 0.4199          | 0.1151 | 0.4651 |
+| 0.5315        | 18.4176 | 12800 | 0.4195          | 0.1149 | 0.4662 |
+| 0.5514        | 18.7055 | 13000 | 0.4195          | 0.1148 | 0.4655 |
+| 0.5629        | 18.9935 | 13200 | 0.4188          | 0.1151 | 0.4667 |
+| 0.5349        | 19.2808 | 13400 | 0.4184          | 0.1145 | 0.4626 |
+| 0.5468        | 19.5688 | 13600 | 0.4176          | 0.1149 | 0.4635 |
+| 0.5396        | 19.8567 | 13800 | 0.4177          | 0.1145 | 0.4635 |
+
+
+### Framework versions
+
+- Transformers 4.52.1
+- Pytorch 2.9.1+cu128
+- Datasets 3.6.0
+- Tokenizers 0.21.4

adapter.bxk.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c866df542b9ca3b1ae5a918f4721ab95d758898999ed9e739c7f5885b328a00
+size 9018880

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": 71,
+  "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": 74,
+  "xvector_output_dim": 512
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e754d283940b06f797389c5605de8e1ce75a7beb551c009f3f5b5a404f68c8ad
+size 3859111256

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 sha256:6a803ae205c1df45e89ea6504f0850538f95afc1473eca0bbff1c07cfab33684
+size 5969

vocab.json

@@ -1,76 +1 @@
-{
-  "bxk": {
-    "'": 8,
-    "(": 45,
-    ")": 19,
-    "-": 68,
-    "...": 69,
-    "0": 28,
-    "1": 65,
-    "2": 49,
-    "5": 35,
-    "6": 2,
-    "9": 29,
-    "@": 52,
-    "A": 5,
-    "B": 30,
-    "C": 6,
-    "D": 7,
-    "E": 9,
-    "F": 27,
-    "G": 61,
-    "H": 22,
-    "I": 59,
-    "K": 1,
-    "L": 57,
-    "M": 48,
-    "N": 53,
-    "O": 67,
-    "P": 41,
-    "S": 20,
-    "T": 47,
-    "U": 56,
-    "V": 54,
-    "W": 4,
-    "Y": 39,
-    "[PAD]": 71,
-    "[UNK]": 70,
-    "a": 13,
-    "b": 66,
-    "c": 11,
-    "ch": 10,
-    "d": 25,
-    "e": 33,
-    "f": 34,
-    "fw": 37,
-    "g": 0,
-    "h": 32,
-    "i": 31,
-    "j": 50,
-    "k": 63,
-    "kh": 42,
-    "l": 24,
-    "ly": 3,
-    "m": 43,
-    "mb": 14,
-    "n": 55,
-    "nd": 62,
-    "ng": 18,
-    "nj": 64,
-    "ny": 40,
-    "o": 16,
-    "p": 21,
-    "q": 58,
-    "r": 23,
-    "s": 44,
-    "sh": 15,
-    "t": 60,
-    "u": 46,
-    "v": 51,
-    "w": 17,
-    "x": 12,
-    "y": 26,
-    "z": 36,
-    "|": 38
-  }
-}
+{"bxk": {"g": 0, "K": 1, "6": 2, "ly": 3, "W": 4, "A": 5, "C": 6, "D": 7, "'": 8, "E": 9, "ch": 10, "c": 11, "x": 12, "a": 13, "mb": 14, "sh": 15, "o": 16, "w": 17, "ng": 18, ")": 19, "S": 20, "p": 21, "H": 22, "r": 23, "l": 24, "d": 25, "y": 26, "F": 27, "0": 28, "9": 29, "B": 30, "i": 31, "h": 32, "e": 33, "f": 34, "5": 35, "z": 36, "fw": 37, "Y": 39, "ny": 40, "P": 41, "kh": 42, "m": 43, "s": 44, "(": 45, "u": 46, "T": 47, "M": 48, "2": 49, "j": 50, "v": 51, "@": 52, "N": 53, "V": 54, "n": 55, "U": 56, "L": 57, "q": 58, "I": 59, "t": 60, "G": 61, "nd": 62, "k": 63, "nj": 64, "1": 65, "b": 66, "O": 67, "-": 68, "|": 38, "...": 69, "[UNK]": 70, "[PAD]": 71}}