MMS (mms-lid-126)

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* 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
+MMS/mms-lid-126/onnx/model.onnx_data filter=lfs diff=lfs merge=lfs -text

MMS/mms-lid-126/.gitattributes

@@ -0,0 +1,36 @@
+*.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
+onnx/model.onnx_data filter=lfs diff=lfs merge=lfs -text

MMS/mms-lid-126/README.md

@@ -0,0 +1,27 @@
+---
+base_model: facebook/mms-lid-126
+library_name: transformers.js
+tags:
+- mms
+---
+
+https://huggingface.co/facebook/mms-lid-126 with ONNX weights to be compatible with Transformers.js.
+
+## Usage (Transformers.js)
+
+If you haven't already, you can install the [Transformers.js](https://huggingface.co/docs/transformers.js) JavaScript library from [NPM](https://www.npmjs.com/package/@huggingface/transformers) using:
+```bash
+npm i @huggingface/transformers
+```
+
+**Example:** Perform language identification.
+
+```js
+import { pipeline } from '@huggingface/transformers';
+
+const classifier = await pipeline('audio-classification', 'Xenova/mms-lid-126');
+const url = 'https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/jfk.wav';
+const output = await classifier(url);
+```
+
+Note: Having a separate repo for ONNX weights is intended to be a temporary solution until WebML gains more traction. If you would like to make your models web-ready, we recommend converting to ONNX using [🤗 Optimum](https://huggingface.co/docs/optimum/index) and structuring your repo like this one (with ONNX weights located in a subfolder named `onnx`).

MMS/mms-lid-126/config.json

@@ -0,0 +1,241 @@
+{
+  "_name_or_path": "facebook/mms-lid-126",
+  "activation_dropout": 0.05,
+  "adapter_attn_dim": 16,
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": false,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForSequenceClassification"
+  ],
+  "attention_dropout": 0.05,
+  "bos_token_id": 1,
+  "classifier_proj_size": 1024,
+  "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": 0.05,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.05,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.05,
+  "hidden_size": 1280,
+  "id2label": {
+    "0": "ara",
+    "1": "cmn",
+    "2": "eng",
+    "3": "spa",
+    "4": "fra",
+    "5": "mlg",
+    "6": "swe",
+    "7": "por",
+    "8": "vie",
+    "9": "ful",
+    "10": "sun",
+    "11": "asm",
+    "12": "ben",
+    "13": "zlm",
+    "14": "kor",
+    "15": "ind",
+    "16": "hin",
+    "17": "tuk",
+    "18": "urd",
+    "19": "aze",
+    "20": "slv",
+    "21": "mon",
+    "22": "hau",
+    "23": "tel",
+    "24": "swh",
+    "25": "bod",
+    "26": "rus",
+    "27": "tur",
+    "28": "heb",
+    "29": "mar",
+    "30": "som",
+    "31": "tgl",
+    "32": "tat",
+    "33": "tha",
+    "34": "cat",
+    "35": "ron",
+    "36": "mal",
+    "37": "bel",
+    "38": "pol",
+    "39": "yor",
+    "40": "nld",
+    "41": "bul",
+    "42": "hat",
+    "43": "afr",
+    "44": "isl",
+    "45": "amh",
+    "46": "tam",
+    "47": "hun",
+    "48": "hrv",
+    "49": "lit",
+    "50": "cym",
+    "51": "fas",
+    "52": "mkd",
+    "53": "ell",
+    "54": "bos",
+    "55": "deu",
+    "56": "sqi",
+    "57": "jav",
+    "58": "nob",
+    "59": "uzb",
+    "60": "snd",
+    "61": "lat",
+    "62": "nya",
+    "63": "grn",
+    "64": "mya",
+    "65": "orm",
+    "66": "lin",
+    "67": "hye",
+    "68": "yue",
+    "69": "pan",
+    "70": "jpn",
+    "71": "kaz",
+    "72": "npi",
+    "73": "kat",
+    "74": "guj",
+    "75": "kan",
+    "76": "tgk",
+    "77": "ukr",
+    "78": "ces",
+    "79": "lav",
+    "80": "bak",
+    "81": "khm",
+    "82": "fao",
+    "83": "glg",
+    "84": "ltz",
+    "85": "lao",
+    "86": "mlt",
+    "87": "sin",
+    "88": "sna",
+    "89": "ita",
+    "90": "srp",
+    "91": "mri",
+    "92": "nno",
+    "93": "pus",
+    "94": "eus",
+    "95": "ory",
+    "96": "lug",
+    "97": "bre",
+    "98": "luo",
+    "99": "slk",
+    "100": "fin",
+    "101": "dan",
+    "102": "yid",
+    "103": "est",
+    "104": "ceb",
+    "105": "war",
+    "106": "san",
+    "107": "kir",
+    "108": "oci",
+    "109": "wol",
+    "110": "haw",
+    "111": "kam",
+    "112": "umb",
+    "113": "xho",
+    "114": "epo",
+    "115": "zul",
+    "116": "ibo",
+    "117": "abk",
+    "118": "ckb",
+    "119": "nso",
+    "120": "gle",
+    "121": "kea",
+    "122": "ast",
+    "123": "sco",
+    "124": "glv",
+    "125": "ina"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 5120,
+  "label2id": null,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.05,
+  "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": 0,
+  "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
+  ],
+  "transformers_version": "4.32.0.dev0",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 154,
+  "xvector_output_dim": 512,
+  "transformers.js_config": {
+    "use_external_data_format": {
+      "model.onnx": true
+    }
+  }
+}

MMS/mms-lid-126/onnx/model.onnx_data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40884ebe045b5ce285fed3c8afaaad571a89070dccfc96cb873cfaaefe480f0e
+size 3863621632

MMS/mms-lid-126/preprocessor_config.json

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

MMS/mms-lid-126/quantize_config.json

@@ -0,0 +1,33 @@
+{
+    "per_channel": true,
+    "reduce_range": true,
+    "per_model_config": {
+        "model": {
+            "op_types": [
+                "Sqrt",
+                "Div",
+                "Identity",
+                "Reshape",
+                "Gather",
+                "Gemm",
+                "Mul",
+                "Shape",
+                "Conv",
+                "Erf",
+                "Unsqueeze",
+                "Pow",
+                "Add",
+                "Concat",
+                "MatMul",
+                "ReduceMean",
+                "Slice",
+                "Softmax",
+                "Transpose",
+                "Relu",
+                "Sub",
+                "Constant"
+            ],
+            "weight_type": "QUInt8"
+        }
+    }
+}

MMS/mms-lid-126/source.txt

@@ -0,0 +1 @@
+https://huggingface.co/Xenova/mms-lid-126