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-ruc-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-ruc-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: 0.4248
+- Cer: 0.1349
+- Wer: 0.5697
+
+## 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    |
+|:-------------:|:-------:|:-----:|:---------------:|:------:|:------:|
+| 1.0456        | 0.2674  | 200   | 0.7005          | 0.1876 | 0.7348 |
+| 0.9305        | 0.5348  | 400   | 0.6500          | 0.1789 | 0.7143 |
+| 0.9102        | 0.8021  | 600   | 0.6226          | 0.1716 | 0.6959 |
+| 0.8748        | 1.0695  | 800   | 0.5937          | 0.1650 | 0.6777 |
+| 0.8449        | 1.3369  | 1000  | 0.5832          | 0.1629 | 0.6735 |
+| 0.8468        | 1.6043  | 1200  | 0.5809          | 0.1629 | 0.6763 |
+| 0.8773        | 1.8717  | 1400  | 0.5673          | 0.1611 | 0.6642 |
+| 0.842         | 2.1390  | 1600  | 0.5611          | 0.1586 | 0.6618 |
+| 0.8072        | 2.4064  | 1800  | 0.5468          | 0.1536 | 0.6484 |
+| 0.8458        | 2.6738  | 2000  | 0.5488          | 0.1543 | 0.6403 |
+| 0.8067        | 2.9412  | 2200  | 0.5323          | 0.1571 | 0.6530 |
+| 0.8039        | 3.2086  | 2400  | 0.5307          | 0.1556 | 0.6467 |
+| 0.7867        | 3.4759  | 2600  | 0.5273          | 0.1519 | 0.6353 |
+| 0.802         | 3.7433  | 2800  | 0.5372          | 0.1537 | 0.6461 |
+| 0.8293        | 4.0107  | 3000  | 0.5359          | 0.1552 | 0.6490 |
+| 0.7776        | 4.2781  | 3200  | 0.5194          | 0.1542 | 0.6411 |
+| 0.7744        | 4.5455  | 3400  | 0.5169          | 0.1512 | 0.6353 |
+| 0.7815        | 4.8128  | 3600  | 0.5188          | 0.1530 | 0.6397 |
+| 0.75          | 5.0802  | 3800  | 0.5100          | 0.1518 | 0.6291 |
+| 0.7806        | 5.3476  | 4000  | 0.5020          | 0.1482 | 0.6220 |
+| 0.7466        | 5.6150  | 4200  | 0.5074          | 0.1523 | 0.6365 |
+| 0.7769        | 5.8824  | 4400  | 0.5069          | 0.1500 | 0.6262 |
+| 0.716         | 6.1497  | 4600  | 0.5062          | 0.1514 | 0.6285 |
+| 0.7188        | 6.4171  | 4800  | 0.4985          | 0.1473 | 0.6136 |
+| 0.7666        | 6.6845  | 5000  | 0.4906          | 0.1461 | 0.6161 |
+| 0.7389        | 6.9519  | 5200  | 0.4812          | 0.1464 | 0.6111 |
+| 0.7356        | 7.2193  | 5400  | 0.4934          | 0.1458 | 0.6193 |
+| 0.7315        | 7.4866  | 5600  | 0.4823          | 0.1452 | 0.6067 |
+| 0.7446        | 7.7540  | 5800  | 0.4818          | 0.1455 | 0.6115 |
+| 0.7463        | 8.0214  | 6000  | 0.4883          | 0.1455 | 0.6085 |
+| 0.715         | 8.2888  | 6200  | 0.4849          | 0.1452 | 0.6092 |
+| 0.7065        | 8.5561  | 6400  | 0.4759          | 0.1442 | 0.6026 |
+| 0.717         | 8.8235  | 6600  | 0.4707          | 0.1433 | 0.5998 |
+| 0.7102        | 9.0909  | 6800  | 0.4627          | 0.1420 | 0.6038 |
+| 0.6856        | 9.3583  | 7000  | 0.4647          | 0.1414 | 0.5957 |
+| 0.7235        | 9.6257  | 7200  | 0.4651          | 0.1425 | 0.6086 |
+| 0.6834        | 9.8930  | 7400  | 0.4635          | 0.1413 | 0.5982 |
+| 0.6923        | 10.1604 | 7600  | 0.4642          | 0.1414 | 0.5999 |
+| 0.7048        | 10.4278 | 7800  | 0.4643          | 0.1419 | 0.5944 |
+| 0.6968        | 10.6952 | 8000  | 0.4584          | 0.1397 | 0.5960 |
+| 0.7231        | 10.9626 | 8200  | 0.4611          | 0.1414 | 0.6021 |
+| 0.6572        | 11.2299 | 8400  | 0.4579          | 0.1404 | 0.5964 |
+| 0.6755        | 11.4973 | 8600  | 0.4573          | 0.1394 | 0.5914 |
+| 0.6942        | 11.7647 | 8800  | 0.4512          | 0.1394 | 0.5889 |
+| 0.6712        | 12.0321 | 9000  | 0.4499          | 0.1395 | 0.5910 |
+| 0.6926        | 12.2995 | 9200  | 0.4522          | 0.1380 | 0.5823 |
+| 0.6955        | 12.5668 | 9400  | 0.4623          | 0.1423 | 0.6001 |
+| 0.6834        | 12.8342 | 9600  | 0.4494          | 0.1381 | 0.5847 |
+| 0.6262        | 13.1016 | 9800  | 0.4451          | 0.1379 | 0.5866 |
+| 0.6621        | 13.3690 | 10000 | 0.4454          | 0.1384 | 0.5841 |
+| 0.6614        | 13.6364 | 10200 | 0.4460          | 0.1383 | 0.5886 |
+| 0.6656        | 13.9037 | 10400 | 0.4423          | 0.1366 | 0.5784 |
+| 0.6491        | 14.1711 | 10600 | 0.4418          | 0.1375 | 0.5815 |
+| 0.6288        | 14.4385 | 10800 | 0.4436          | 0.1367 | 0.5761 |
+| 0.6544        | 14.7059 | 11000 | 0.4349          | 0.1360 | 0.5767 |
+| 0.6391        | 14.9733 | 11200 | 0.4369          | 0.1360 | 0.5738 |
+| 0.6572        | 15.2406 | 11400 | 0.4402          | 0.1354 | 0.5772 |
+| 0.6427        | 15.5080 | 11600 | 0.4383          | 0.1357 | 0.5733 |
+| 0.6382        | 15.7754 | 11800 | 0.4360          | 0.1361 | 0.5727 |
+| 0.6314        | 16.0428 | 12000 | 0.4368          | 0.1359 | 0.5743 |
+| 0.6525        | 16.3102 | 12200 | 0.4375          | 0.1354 | 0.5742 |
+| 0.6267        | 16.5775 | 12400 | 0.4325          | 0.1351 | 0.5713 |
+| 0.6299        | 16.8449 | 12600 | 0.4336          | 0.1348 | 0.5703 |
+| 0.6261        | 17.1123 | 12800 | 0.4294          | 0.1356 | 0.5758 |
+| 0.6182        | 17.3797 | 13000 | 0.4301          | 0.1356 | 0.5701 |
+| 0.6048        | 17.6471 | 13200 | 0.4311          | 0.1360 | 0.5743 |
+| 0.634         | 17.9144 | 13400 | 0.4303          | 0.1344 | 0.5644 |
+| 0.6001        | 18.1818 | 13600 | 0.4289          | 0.1363 | 0.5727 |
+| 0.6674        | 18.4492 | 13800 | 0.4282          | 0.1351 | 0.5697 |
+| 0.6198        | 18.7166 | 14000 | 0.4261          | 0.1342 | 0.5656 |
+| 0.6218        | 18.9840 | 14200 | 0.4255          | 0.1354 | 0.5699 |
+| 0.6215        | 19.2513 | 14400 | 0.4254          | 0.1354 | 0.5708 |
+| 0.6267        | 19.5187 | 14600 | 0.4250          | 0.1345 | 0.5676 |
+| 0.6536        | 19.7861 | 14800 | 0.4248          | 0.1349 | 0.5697 |
+
+
+### Framework versions
+
+- Transformers 4.52.1
+- Pytorch 2.9.1+cu128
+- Datasets 3.6.0
+- Tokenizers 0.21.4

adapter.ruc.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9eff23c694c102016678fef947ae08acca0b3205808e10ce5f9a83177cf27cc9
+size 8957392

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": 59,
+  "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": 62,
+  "xvector_output_dim": 512
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47455947d9a8210387b97572d9e5b4c9fc4512505e88fa13823a5afce6eefd3c
+size 3859049768

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 sha256:3974a2c84f2f45b413b92546f8bbdb0a6e21f5f0dcba1e68b9747011625661f5
+size 5969

vocab.json

@@ -1,64 +1 @@
-{
-  "ruc": {
-    "'": 21,
-    "-": 48,
-    ".": 34,
-    "...": 57,
-    "A": 46,
-    "B": 47,
-    "C": 8,
-    "E": 53,
-    "F": 17,
-    "G": 28,
-    "H": 29,
-    "I": 42,
-    "J": 9,
-    "K": 50,
-    "L": 40,
-    "M": 7,
-    "N": 25,
-    "O": 11,
-    "R": 18,
-    "S": 36,
-    "T": 27,
-    "U": 22,
-    "V": 3,
-    "W": 54,
-    "Y": 51,
-    "Z": 4,
-    "[PAD]": 59,
-    "[UNK]": 58,
-    "a": 19,
-    "b": 2,
-    "bb": 30,
-    "c": 33,
-    "d": 13,
-    "dd": 14,
-    "e": 23,
-    "f": 38,
-    "g": 41,
-    "gy": 10,
-    "h": 55,
-    "i": 52,
-    "j": 15,
-    "k": 39,
-    "ky": 26,
-    "l": 1,
-    "m": 6,
-    "n": 0,
-    "ng": 43,
-    "o": 31,
-    "p": 5,
-    "r": 32,
-    "s": 35,
-    "sy": 44,
-    "t": 16,
-    "u": 12,
-    "v": 20,
-    "w": 49,
-    "x": 37,
-    "y": 56,
-    "z": 45,
-    "|": 24
-  }
-}
+{"ruc": {"n": 0, "l": 1, "b": 2, "V": 3, "Z": 4, "p": 5, "m": 6, "M": 7, "C": 8, "J": 9, "gy": 10, "O": 11, "u": 12, "d": 13, "dd": 14, "j": 15, "t": 16, "F": 17, "R": 18, "a": 19, "v": 20, "'": 21, "U": 22, "e": 23, "N": 25, "ky": 26, "T": 27, "G": 28, "H": 29, "bb": 30, "o": 31, "r": 32, "c": 33, ".": 34, "s": 35, "S": 36, "x": 37, "f": 38, "k": 39, "L": 40, "g": 41, "I": 42, "ng": 43, "sy": 44, "z": 45, "A": 46, "B": 47, "-": 48, "w": 49, "K": 50, "Y": 51, "i": 52, "E": 53, "W": 54, "h": 55, "y": 56, "|": 24, "...": 57, "[UNK]": 58, "[PAD]": 59}}