adding transcriber script

app.py

@@ -0,0 +1,30 @@
+from transformers import pipeline
+import gradio as gr
+
+local_model_name = "wav2vec2_model_pipeline"
+speech_recognizer = pipeline("automatic-speech-recognition", model = f"models/{local_model_name}")
+
+def greet_and_transcribe(name, intensity, input_audio):
+    input_audio_rs = librosa.resample(
+        input_audio[1].astype(float),
+        orig_sr=input_audio[0],
+        target_sr=speech_recognizer.feature_extractor.sampling_rate)
+    transcribed_audio = speech_recognizer(input_audio_rs)["text"]
+    return "Hello, " + name + "!" * int(intensity), transcribed_audio
+
+demo = gr.Interface(
+    title="A simple audio transcribing model",
+    description="This is an application to test gradio functionalities",
+
+    fn=greet_and_transcribe,
+    inputs=[
+        gr.Text(placeholder="input your name here"),
+        gr.Slider(minimum=1, maximum=5, value=3),
+        gr.Audio()],
+    outputs=["text", "text"],
+    cache_examples="lazy"
+    allow_flagging="auto",
+    # article="<p style='text-align: center'><a href='https://tmabraham.github.io/blog/gradio_hf_spaces_tutorial' target='_blank'>Blog post</a></p>"
+    enable_queue=True
+)
+demo.launch(share=True)

wav2vec2_model_pipeline/config.json

@@ -0,0 +1,110 @@
+{
+  "_name_or_path": "facebook/wav2vec2-base-960h",
+  "activation_dropout": 0.1,
+  "adapter_attn_dim": null,
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": false,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForCTC"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "codevector_dim": 256,
+  "contrastive_logits_temperature": 0.1,
+  "conv_bias": false,
+  "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": "sum",
+  "ctc_zero_infinity": false,
+  "diversity_loss_weight": 0.1,
+  "do_stable_layer_norm": false,
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_dropout": 0.0,
+  "feat_extract_norm": "group",
+  "feat_proj_dropout": 0.1,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.1,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.1,
+  "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": 12,
+  "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": 12,
+  "num_negatives": 100,
+  "output_hidden_size": 768,
+  "pad_token_id": 0,
+  "proj_codevector_dim": 256,
+  "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": "4.41.2",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 32,
+  "xvector_output_dim": 512
+}

wav2vec2_model_pipeline/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ecc0894f391d5a74a066563afb948f12e0b60118d6958a62276bbb062546149d
+size 377611120

wav2vec2_model_pipeline/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": false,
+  "sampling_rate": 16000
+}

wav2vec2_model_pipeline/special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

wav2vec2_model_pipeline/tokenizer_config.json

@@ -0,0 +1,49 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "do_lower_case": false,
+  "do_normalize": true,
+  "eos_token": "</s>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "replace_word_delimiter_char": " ",
+  "return_attention_mask": false,
+  "target_lang": null,
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "<unk>",
+  "word_delimiter_token": "|"
+}

wav2vec2_model_pipeline/vocab.json

@@ -0,0 +1,34 @@
+{
+  "'": 27,
+  "</s>": 2,
+  "<pad>": 0,
+  "<s>": 1,
+  "<unk>": 3,
+  "A": 7,
+  "B": 24,
+  "C": 19,
+  "D": 14,
+  "E": 5,
+  "F": 20,
+  "G": 21,
+  "H": 11,
+  "I": 10,
+  "J": 29,
+  "K": 26,
+  "L": 15,
+  "M": 17,
+  "N": 9,
+  "O": 8,
+  "P": 23,
+  "Q": 30,
+  "R": 13,
+  "S": 12,
+  "T": 6,
+  "U": 16,
+  "V": 25,
+  "W": 18,
+  "X": 28,
+  "Y": 22,
+  "Z": 31,
+  "|": 4
+}