Upload folder using huggingface_hub

.gitattributes

@@ -1,35 +1,18 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin.* filter=lfs diff=lfs merge=lfs -text
+*.lfs.* 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
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tar.gz filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.ftz 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
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+language_model/gujarati_try.binary filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,123 @@
+---
+language: gu
+datasets:
+- openslr
+metrics:
+- wer
+tags:
+- audio
+- automatic-speech-recognition
+- speech
+- xlsr-fine-tuning-week
+license: apache-2.0
+model-index:
+- name: XLSR Wav2Vec2 Large 53 Gujarati by Gunjan Chhablani
+  results:
+  - task: 
+      name: Speech Recognition
+      type: automatic-speech-recognition
+    dataset:
+      name: OpenSLR gu
+      type: openslr
+    metrics:
+       - name: Test WER
+         type: wer
+         value: 23.55
+---
+
+# Wav2Vec2-Large-XLSR-53-Gujarati
+
+Fine-tuned [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on Gujarati using the [OpenSLR SLR78](http://openslr.org/78/) dataset. When using this model, make sure that your speech input is sampled at 16kHz. 
+
+## Usage
+
+The model can be used directly (without a language model) as follows, assuming you have a dataset with Gujarati `sentence` and `path` fields:
+
+```python
+import torch
+import torchaudio
+from datasets import load_dataset
+from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
+
+# test_dataset = #TODO: WRITE YOUR CODE TO LOAD THE TEST DATASET. 
+# For sample see the Colab link in Training Section.
+
+processor = Wav2Vec2Processor.from_pretrained("gchhablani/wav2vec2-large-xlsr-gu")
+model = Wav2Vec2ForCTC.from_pretrained("gchhablani/wav2vec2-large-xlsr-gu")
+
+resampler = torchaudio.transforms.Resample(48_000, 16_000) # The original data was with 48,000 sampling rate. You can change it according to your input.
+
+# Preprocessing the datasets.
+# We need to read the audio files as arrays
+def speech_file_to_array_fn(batch):
+    speech_array, sampling_rate = torchaudio.load(batch["path"])
+    batch["speech"] = resampler(speech_array).squeeze().numpy()
+    return batch
+
+test_dataset_eval = test_dataset_eval.map(speech_file_to_array_fn)
+inputs = processor(test_dataset_eval["speech"][:2], sampling_rate=16_000, return_tensors="pt", padding=True)
+
+with torch.no_grad():
+    logits = model(inputs.input_values, attention_mask=inputs.attention_mask).logits
+
+predicted_ids = torch.argmax(logits, dim=-1)
+
+print("Prediction:", processor.batch_decode(predicted_ids))
+print("Reference:", test_dataset_eval["sentence"][:2])
+```
+
+
+## Evaluation
+
+The model can be evaluated as follows on 10% of the Marathi data on OpenSLR.
+
+```python
+import torch
+import torchaudio
+from datasets import load_dataset, load_metric
+from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
+import re
+
+# test_dataset = #TODO: WRITE YOUR CODE TO LOAD THE TEST DATASET. For sample see the Colab link in Training Section.
+
+wer = load_metric("wer")
+
+processor = Wav2Vec2Processor.from_pretrained("gchhablani/wav2vec2-large-xlsr-gu")
+model = Wav2Vec2ForCTC.from_pretrained("gchhablani/wav2vec2-large-xlsr-gu")
+model.to("cuda")
+
+chars_to_ignore_regex = '[\,\?\.\!\-\;\:\"\“\%\‘\”\�\–\…\'\_\’]'
+resampler = torchaudio.transforms.Resample(48_000, 16_000)
+
+# Preprocessing the datasets.
+# We need to read the audio files as arrays
+def speech_file_to_array_fn(batch):
+    batch["sentence"] = re.sub(chars_to_ignore_regex, '', batch["sentence"]).lower()
+    speech_array, sampling_rate = torchaudio.load(batch["path"])
+    batch["speech"] = resampler(speech_array).squeeze().numpy()
+    return batch
+
+test_dataset = test_dataset.map(speech_file_to_array_fn)
+
+# Preprocessing the datasets.
+# We need to read the aduio files as arrays
+def evaluate(batch):
+    inputs = processor(batch["speech"], sampling_rate=16_000, return_tensors="pt", padding=True)
+    with torch.no_grad():
+        logits = model(inputs.input_values.to("cuda"), 
+        attention_mask=inputs.attention_mask.to("cuda")).logits
+        pred_ids = torch.argmax(logits, dim=-1)
+        batch["pred_strings"] = processor.batch_decode(pred_ids)
+        return batch
+
+result = test_dataset.map(evaluate, batched=True, batch_size=8)
+
+print("WER: {:2f}".format(100 * wer.compute(predictions=result["pred_strings"], references=result["sentence"])))
+```
+
+**Test Result**: 23.55 %  
+
+## Training
+
+90% of the OpenSLR Gujarati Male+Female dataset was used for training, after removing few examples that contained Roman characters.
+The colab notebook used for training can be found [here](https://colab.research.google.com/drive/1fRQlgl4EPR4qKGScgza3MpWgbL5BeWtn?usp=sharing). 

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 81,
+  "<s>": 80
+}

alphabet.json

@@ -0,0 +1 @@
+{"labels": ["\u0a8f", "\u0a82", "\u0a88", "\u0ac8", "\u0ac0", "\u0aa3", "\u0ab9", "\u0ae6", "\u0a93", "\u0ac5", "\u0aaf", "\u0aa4", "\u0a8d", "\u0ab7", "\u0a94", "\u0aa0", "\u0a89", "\u0a9b", "\u0aae", "\u0a86", "\u0aa8", "\u0abc", "\u0a95", "\u0ab2", "\u0acb", "\u0aea", "\u0ae8", "\u0aeb", "\u0aa1", "\u0aab", "\u0a98", "\u0aed", "\u0aee", "\u0abe", "\u0acd", "\u0a81", "\u0a90", "\u0a9d", "\u0ac3", "\u200d", "\u0aa2", "\u0a83", "\u0ab5", " ", "\u0a9c", "\u0aaa", "\u0abf", "\u0a97", "\u0aa5", "\u0aef", "\u0acc", "\u0a91", "\u0ac7", "\u0ae0", "\u0a96", "\u0a87", "\u0a85", "\u0a8b", "\u0ae9", "\u0ac1", "\u0aac", "\u0ab3", "\u0ac9", "\u0aec", "\u200c", "\u0aa6", "\u0ac2", "\u0a8a", "\u0ae2", "\u0ab8", "\u0ab6", "\u0ae7", "\u0a9a", "\u0aa7", "\u0ab0", "\u0a9e", "\u0a9f", "\u0aad", "\u2047", "", "<s>", "</s>"], "is_bpe": false}

config.json

@@ -0,0 +1,76 @@
+{
+  "_name_or_path": "facebook/wav2vec2-large-xlsr-53",
+  "activation_dropout": 0.0,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForCTC"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 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,
+  "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,
+  "final_dropout": 0.0,
+  "gradient_checkpointing": true,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.1,
+  "mask_channel_length": 10,
+  "mask_channel_min_space": 1,
+  "mask_channel_other": 0.0,
+  "mask_channel_prob": 0.0,
+  "mask_channel_selection": "static",
+  "mask_feature_length": 10,
+  "mask_feature_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_min_space": 1,
+  "mask_time_other": 0.0,
+  "mask_time_prob": 0.05,
+  "mask_time_selection": "static",
+  "model_type": "wav2vec2",
+  "num_attention_heads": 16,
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 128,
+  "num_feat_extract_layers": 7,
+  "num_hidden_layers": 24,
+  "pad_token_id": 79,
+  "transformers_version": "4.5.0.dev0",
+  "vocab_size": 80
+}

flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc30369cb6d5846ce73104b7f6867bc00352eea0318cfdc3cbbe860881f8b84
+size 135

language_model/attrs.json

@@ -0,0 +1 @@
+{"alpha": 0.5, "beta": 1.5, "unk_score_offset": -10.0, "score_boundary": true}

preprocessor_config.json

@@ -0,0 +1,10 @@
+{
+  "do_normalize": true,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "processor_class": "Wav2Vec2ProcessorWithLM",
+  "return_attention_mask": true,
+  "sampling_rate": 16000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14d3e31303a48bced2db54cad006a078f9955ee42b9fabc7a9ca51da9e82d4ff
+size 1262261847

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "[PAD]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,48 @@
+{
+  "added_tokens_decoder": {
+    "78": {
+      "content": "[UNK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "79": {
+      "content": "[PAD]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "80": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "81": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "processor_class": "Wav2Vec2ProcessorWithLM",
+  "replace_word_delimiter_char": " ",
+  "target_lang": null,
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "[UNK]",
+  "word_delimiter_token": "|"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9cedeed8072ec2cf45c9812dafcd6855a08d7f57102501d8921dbe318e40fdc
+size 2287

vocab.json

@@ -0,0 +1,82 @@
+{
+  "[PAD]": 79,
+  "[UNK]": 78,
+  "|": 43,
+  "ઁ": 35,
+  "ં": 1,
+  "ઃ": 41,
+  "અ": 56,
+  "આ": 19,
+  "ઇ": 55,
+  "ઈ": 2,
+  "ઉ": 16,
+  "ઊ": 67,
+  "ઋ": 57,
+  "ઍ": 12,
+  "એ": 0,
+  "ઐ": 36,
+  "ઑ": 51,
+  "ઓ": 8,
+  "ઔ": 14,
+  "ક": 22,
+  "ખ": 54,
+  "ગ": 47,
+  "ઘ": 30,
+  "ચ": 72,
+  "છ": 17,
+  "જ": 44,
+  "ઝ": 37,
+  "ઞ": 75,
+  "ટ": 76,
+  "ઠ": 15,
+  "ડ": 28,
+  "ઢ": 40,
+  "ણ": 5,
+  "ત": 11,
+  "થ": 48,
+  "દ": 65,
+  "ધ": 73,
+  "ન": 20,
+  "પ": 45,
+  "ફ": 29,
+  "બ": 60,
+  "ભ": 77,
+  "મ": 18,
+  "ય": 10,
+  "ર": 74,
+  "લ": 23,
+  "ળ": 61,
+  "વ": 42,
+  "શ": 70,
+  "ષ": 13,
+  "સ": 69,
+  "હ": 6,
+  "઼": 21,
+  "ા": 33,
+  "િ": 46,
+  "ી": 4,
+  "ુ": 59,
+  "ૂ": 66,
+  "ૃ": 38,
+  "ૅ": 9,
+  "ે": 52,
+  "ૈ": 3,
+  "ૉ": 62,
+  "ો": 24,
+  "ૌ": 50,
+  "્": 34,
+  "ૠ": 53,
+  "ૢ": 68,
+  "૦": 7,
+  "૧": 71,
+  "૨": 26,
+  "૩": 58,
+  "૪": 25,
+  "૫": 27,
+  "૬": 63,
+  "૭": 31,
+  "૮": 32,
+  "૯": 49,
+  "‌": 64,
+  "‍": 39
+}