End of training

README.md

@@ -1,199 +1,139 @@
 ---
 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-pne-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-pne-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: 0.3988
+- Cer: 0.1116
+- Wer: 0.3299
+
+## 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    |
+|:-------------:|:-------:|:-----:|:---------------:|:------:|:------:|
+| 1.2889        | 0.2685  | 200   | 0.8402          | 0.2271 | 0.6489 |
+| 1.0716        | 0.5369  | 400   | 0.6725          | 0.1834 | 0.5259 |
+| 0.9362        | 0.8054  | 600   | 0.6121          | 0.1678 | 0.4840 |
+| 0.89          | 1.0738  | 800   | 0.5791          | 0.1584 | 0.4544 |
+| 0.8681        | 1.3423  | 1000  | 0.5532          | 0.1530 | 0.4397 |
+| 0.8789        | 1.6107  | 1200  | 0.5536          | 0.1538 | 0.4418 |
+| 0.8424        | 1.8792  | 1400  | 0.5269          | 0.1464 | 0.4200 |
+| 0.826         | 2.1477  | 1600  | 0.5185          | 0.1424 | 0.4075 |
+| 0.8315        | 2.4161  | 1800  | 0.5052          | 0.1396 | 0.4019 |
+| 0.8123        | 2.6846  | 2000  | 0.5048          | 0.1379 | 0.3952 |
+| 0.8159        | 2.9530  | 2200  | 0.4888          | 0.1363 | 0.3919 |
+| 0.7834        | 3.2215  | 2400  | 0.4804          | 0.1347 | 0.3854 |
+| 0.7479        | 3.4899  | 2600  | 0.4968          | 0.1371 | 0.3953 |
+| 0.7565        | 3.7584  | 2800  | 0.4762          | 0.1315 | 0.3734 |
+| 0.7769        | 4.0268  | 3000  | 0.4869          | 0.1315 | 0.3744 |
+| 0.702         | 4.2953  | 3200  | 0.4835          | 0.1317 | 0.3775 |
+| 0.7573        | 4.5638  | 3400  | 0.4771          | 0.1295 | 0.3676 |
+| 0.7165        | 4.8322  | 3600  | 0.4696          | 0.1272 | 0.3646 |
+| 0.7126        | 5.1007  | 3800  | 0.4942          | 0.1339 | 0.3843 |
+| 0.7197        | 5.3691  | 4000  | 0.4670          | 0.1268 | 0.3628 |
+| 0.7472        | 5.6376  | 4200  | 0.4651          | 0.1273 | 0.3646 |
+| 0.7005        | 5.9060  | 4400  | 0.4690          | 0.1316 | 0.3830 |
+| 0.7072        | 6.1745  | 4600  | 0.4853          | 0.1306 | 0.3767 |
+| 0.6864        | 6.4430  | 4800  | 0.4825          | 0.1261 | 0.3587 |
+| 0.6764        | 6.7114  | 5000  | 0.4550          | 0.1258 | 0.3614 |
+| 0.763         | 6.9799  | 5200  | 0.4843          | 0.1281 | 0.3678 |
+| 0.7177        | 7.2483  | 5400  | 0.4715          | 0.1276 | 0.3667 |
+| 0.6742        | 7.5168  | 5600  | 0.4600          | 0.1248 | 0.3589 |
+| 0.6795        | 7.7852  | 5800  | 0.5308          | 0.1275 | 0.3692 |
+| 0.7109        | 8.0537  | 6000  | 0.4499          | 0.1226 | 0.3550 |
+| 0.6684        | 8.3221  | 6200  | 0.4773          | 0.1299 | 0.3773 |
+| 0.6827        | 8.5906  | 6400  | 0.4802          | 0.1260 | 0.3631 |
+| 0.6555        | 8.8591  | 6600  | 0.4561          | 0.1249 | 0.3611 |
+| 0.6481        | 9.1275  | 6800  | 0.4601          | 0.1302 | 0.3848 |
+| 0.6913        | 9.3960  | 7000  | 0.4303          | 0.1184 | 0.3415 |
+| 0.661         | 9.6644  | 7200  | 0.4449          | 0.1193 | 0.3452 |
+| 0.628         | 9.9329  | 7400  | 0.4491          | 0.1213 | 0.3518 |
+| 0.6669        | 10.2013 | 7600  | 0.4299          | 0.1185 | 0.3446 |
+| 0.6471        | 10.4698 | 7800  | 0.4364          | 0.1210 | 0.3531 |
+| 0.6254        | 10.7383 | 8000  | 0.4457          | 0.1240 | 0.3642 |
+| 0.6406        | 11.0067 | 8200  | 0.4365          | 0.1199 | 0.3503 |
+| 0.6053        | 11.2752 | 8400  | 0.4365          | 0.1162 | 0.3345 |
+| 0.6322        | 11.5436 | 8600  | 0.4191          | 0.1171 | 0.3405 |
+| 0.6391        | 11.8121 | 8800  | 0.4088          | 0.1141 | 0.3289 |
+| 0.6205        | 12.0805 | 9000  | 0.4149          | 0.1141 | 0.3301 |
+| 0.6313        | 12.3490 | 9200  | 0.4185          | 0.1171 | 0.3431 |
+| 0.6017        | 12.6174 | 9400  | 0.4075          | 0.1157 | 0.3400 |
+| 0.6437        | 12.8859 | 9600  | 0.4050          | 0.1132 | 0.3292 |
+| 0.6354        | 13.1544 | 9800  | 0.4087          | 0.1153 | 0.3359 |
+| 0.6149        | 13.4228 | 10000 | 0.4035          | 0.1134 | 0.3267 |
+| 0.6002        | 13.6913 | 10200 | 0.3985          | 0.1135 | 0.3292 |
+| 0.6098        | 13.9597 | 10400 | 0.4298          | 0.1180 | 0.3492 |
+| 0.5787        | 14.2282 | 10600 | 0.4065          | 0.1144 | 0.3333 |
+| 0.6282        | 14.4966 | 10800 | 0.4057          | 0.1149 | 0.3358 |
+| 0.5775        | 14.7651 | 11000 | 0.4188          | 0.1175 | 0.3471 |
+| 0.595         | 15.0336 | 11200 | 0.4063          | 0.1144 | 0.3354 |
+| 0.6184        | 15.3020 | 11400 | 0.4004          | 0.1125 | 0.3300 |
+| 0.5909        | 15.5705 | 11600 | 0.4156          | 0.1157 | 0.3431 |
+| 0.5826        | 15.8389 | 11800 | 0.4147          | 0.1172 | 0.3476 |
+| 0.5858        | 16.1074 | 12000 | 0.4010          | 0.1129 | 0.3346 |
+| 0.5793        | 16.3758 | 12200 | 0.3852          | 0.1089 | 0.3154 |
+| 0.5661        | 16.6443 | 12400 | 0.3964          | 0.1109 | 0.3229 |
+| 0.5861        | 16.9128 | 12600 | 0.3976          | 0.1120 | 0.3283 |
+| 0.585         | 17.1812 | 12800 | 0.3937          | 0.1108 | 0.3231 |
+| 0.5873        | 17.4497 | 13000 | 0.4106          | 0.1142 | 0.3392 |
+| 0.5572        | 17.7181 | 13200 | 0.3959          | 0.1120 | 0.3320 |
+| 0.5958        | 17.9866 | 13400 | 0.4018          | 0.1118 | 0.3301 |
+| 0.5597        | 18.2550 | 13600 | 0.3958          | 0.1129 | 0.3347 |
+| 0.5559        | 18.5235 | 13800 | 0.3987          | 0.1105 | 0.3255 |
+| 0.5951        | 18.7919 | 14000 | 0.3957          | 0.1097 | 0.3217 |
+| 0.5752        | 19.0604 | 14200 | 0.3935          | 0.1116 | 0.3298 |
+| 0.5571        | 19.3289 | 14400 | 0.4006          | 0.1115 | 0.3292 |
+| 0.5683        | 19.5973 | 14600 | 0.4020          | 0.1122 | 0.3329 |
+| 0.5625        | 19.8658 | 14800 | 0.3988          | 0.1116 | 0.3299 |
+
+
+### Framework versions
+
+- Transformers 4.52.1
+- Pytorch 2.9.1+cu128
+- Datasets 3.6.0
+- Tokenizers 0.21.4

adapter.pne.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5bf11fe335d6da117be72eff76cbf89ecd6e056af3ba9a3b41b723aae397082f
+size 8926640

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": 53,
+  "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": 56,
+  "xvector_output_dim": 512
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a93f35a9d7d87f81604e81c43186e876d51b2101a7dd1c36090f83cd984b1ba
+size 3859019024

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 sha256:479cce9cc5b493ecaa2805e81220df867b1f949a02ed9d00d65827f01ce4af8b
+size 5969

vocab.json

@@ -1,58 +1 @@
-{
-  "pne": {
-    "'": 18,
-    "-": 27,
-    ".": 23,
-    "...": 51,
-    "A": 24,
-    "B": 36,
-    "C": 30,
-    "D": 0,
-    "E": 31,
-    "H": 46,
-    "I": 28,
-    "J": 50,
-    "K": 13,
-    "L": 35,
-    "M": 12,
-    "N": 45,
-    "O": 32,
-    "P": 37,
-    "R": 8,
-    "S": 26,
-    "T": 49,
-    "U": 17,
-    "V": 29,
-    "Y": 9,
-    "[PAD]": 53,
-    "[UNK]": 52,
-    "a": 2,
-    "b": 47,
-    "c": 3,
-    "d": 25,
-    "e": 11,
-    "f": 40,
-    "g": 6,
-    "h": 1,
-    "i": 19,
-    "j": 22,
-    "k": 7,
-    "l": 41,
-    "m": 16,
-    "n": 33,
-    "ng": 15,
-    "o": 48,
-    "p": 38,
-    "q": 20,
-    "r": 34,
-    "s": 14,
-    "t": 5,
-    "u": 4,
-    "v": 21,
-    "w": 10,
-    "x": 43,
-    "y": 39,
-    "z": 42,
-    "|": 44
-  }
-}
+{"pne": {"D": 0, "h": 1, "a": 2, "c": 3, "u": 4, "t": 5, "g": 6, "k": 7, "R": 8, "Y": 9, "w": 10, "e": 11, "M": 12, "K": 13, "s": 14, "ng": 15, "m": 16, "U": 17, "'": 18, "i": 19, "q": 20, "v": 21, "j": 22, ".": 23, "A": 24, "d": 25, "S": 26, "-": 27, "I": 28, "V": 29, "C": 30, "E": 31, "O": 32, "n": 33, "r": 34, "L": 35, "B": 36, "P": 37, "p": 38, "y": 39, "f": 40, "l": 41, "z": 42, "x": 43, "N": 45, "H": 46, "b": 47, "o": 48, "T": 49, "J": 50, "|": 44, "...": 51, "[UNK]": 52, "[PAD]": 53}}