initial commit

.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
+*.arpa filter=lfs diff=lfs merge=lfs -text

ctc_lin.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ab1796261dddd41f3d25a7444d6e229475b0a46c935917578363aa440bcc6d7
+size 2050983

enc.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8badca04f7878950012cfbed3864b263e3326d34232cc171a2bc466e78b91490
+size 12650406

hyperparams.yaml

@@ -0,0 +1,64 @@
+# modules params
+# (nb_tokens, blank_index, bos_index and eos_index must be constistent with
+# pretrained tokenizer)
+nb_tokens: 500
+blank_index: 0
+sample_rate: 16000
+wav2vec2_hub: LeBenchmark/wav2vec2-FR-7K-large
+wav2vec_output_dim: 1024
+nb_enc_neurons: 1024
+enc_drop_out: 0.25
+
+## modules
+
+tokenizer: !new:sentencepiece.SentencePieceProcessor
+
+wav2vec2: !new:speechbrain.lobes.models.huggingface_wav2vec.HuggingFaceWav2Vec2
+    source: !ref <wav2vec2_hub>
+    output_norm: True
+    freeze: True
+    save_path: pretrained_models
+
+enc: !new:speechbrain.nnet.containers.Sequential
+    input_shape: [null, null, !ref <wav2vec_output_dim>]
+    linear1: !name:speechbrain.nnet.linear.Linear
+        n_neurons: !ref <nb_enc_neurons>
+        bias: True
+    bn1: !name:speechbrain.nnet.normalization.BatchNorm1d
+    activation: !new:torch.nn.LeakyReLU
+    drop: !new:torch.nn.Dropout
+        p: !ref <enc_drop_out>
+    linear2: !name:speechbrain.nnet.linear.Linear
+        n_neurons: !ref <nb_enc_neurons>
+        bias: True
+    bn2: !name:speechbrain.nnet.normalization.BatchNorm1d
+    activation2: !new:torch.nn.LeakyReLU
+    drop2: !new:torch.nn.Dropout
+        p: !ref <enc_drop_out>
+    linear3: !name:speechbrain.nnet.linear.Linear
+        n_neurons: !ref <nb_enc_neurons>
+        bias: True
+    bn3: !name:speechbrain.nnet.normalization.BatchNorm1d
+    activation3: !new:torch.nn.LeakyReLU
+
+ctc_lin: !new:speechbrain.nnet.linear.Linear
+    input_size: !ref <nb_enc_neurons>
+    n_neurons: !ref <nb_tokens>
+
+decoding_function: !name:speechbrain.decoders.ctc_greedy_decode
+    blank_id: !ref <blank_index>
+
+encoder: !new:speechbrain.nnet.containers.LengthsCapableSequential
+  wav2vec2: !ref <wav2vec2>
+  enc: !ref <enc>
+  ctc_lin: !ref <ctc_lin>
+
+modules:
+  encoder: !ref <encoder>
+
+pretrainer: !new:speechbrain.utils.parameter_transfer.Pretrainer
+  loadables:
+    wav2vec2: !ref <wav2vec2>
+    enc: !ref <enc>
+    ctc_lin: !ref <ctc_lin>
+    tokenizer: !ref <tokenizer>

model.arpa

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76a37103be16c2be295756531ce5307cb613842cef866658816fee696956165b
+size 959190366

tokenizer.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:521dc4cb2a25a5a71faf12f2532eee80f54d1f64bc42c783790e43fe688b3b37
+size 244727

wav2vec2.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6cb7bf0e9a802aa4278208df571fc83200802cc80b83987d1d3e6a225514ad18
+size 1261917237