Added Models

README.md

@@ -1,3 +1,37 @@
 ---
+language: id
 license: apache-2.0
+tags:
+  - icefall
+  - sherpa-ncnn
+  - phoneme-recognition
+  - automatic-speech-recognition
+datasets:
+  - mozilla-foundation/common_voice_13_0
+  - indonesian-nlp/librivox-indonesia
+  - google/fleurs
 ---
+
+# Sherpa-ncnn Pruned Stateless Zipformer RNN-T Streaming ID
+
+Sherpa-ncnn Pruned Stateless Zipformer RNN-T Streaming ID is an automatic speech recognition model trained on the following datasets:
+
+- [Common Voice ID](https://huggingface.co/datasets/mozilla-foundation/common_voice_13_0)
+- [LibriVox Indonesia](https://huggingface.co/datasets/indonesian-nlp/librivox-indonesia)
+- [FLEURS ID](https://huggingface.co/datasets/google/fleurs)
+
+Instead of being trained to predict sequences of words, this model was trained to predict sequence of phonemes, e.g. `['p', 'ə', 'r', 'b', 'u', 'a', 't', 'a', 'n', 'ɲ', 'a']`. Therefore, the model's [vocabulary](https://huggingface.co/bookbot/pruned-transducer-stateless7-streaming-id/blob/main/data/lang_phone/tokens.txt) contains the different IPA phonemes found in [g2p ID](https://github.com/bookbot-kids/g2p_id).
+
+This model was converted from the TorchScript version of [Pruned Stateless Zipformer RNN-T Streaming ID](https://huggingface.co/bookbot/pruned-transducer-stateless7-streaming-id) to ncnn format.
+
+## Converting from TorchScript
+
+Refer to the [official instructions](https://icefall.readthedocs.io/en/latest/model-export/export-ncnn-zipformer.html) for conversion to ncnn, which includes installation of `csukuangfj`'s [ncnn](https://github.com/csukuangfj/ncnn) fork.
+
+## Frameworks
+
+- [k2](https://github.com/k2-fsa/k2)
+- [icefall](https://github.com/bookbot-hive/icefall)
+- [lhotse](https://github.com/bookbot-hive/lhotse)
+- [sherpa-ncnn](https://github.com/k2-fsa/sherpa-ncnn)
+- [ncnn](https://github.com/csukuangfj/ncnn)

decoder_jit_trace-pnnx.ncnn.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40f08148bbb20bb7f7160ce2419dbd9603b68dbdb3873354ae57a9390f095112
+size 41992

decoder_jit_trace-pnnx.ncnn.param

@@ -0,0 +1,8 @@
+7767517
+6 6
+Input                    in0                      0 1 in0
+Embed                    embed_1                  1 1 in0 1 0=512 1=33 2=0 3=16896
+Permute                  permute_2                1 1 1 2 0=1
+ConvolutionDepthWise1D   convdw1d_4               1 1 2 3 0=512 1=2 2=1 3=1 4=0 5=0 6=4096 7=128
+Permute                  permute_3                1 1 3 4 0=1
+ReLU                     relu_0                   1 1 4 out0

encoder_jit_trace-pnnx.ncnn.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35390708cdae1a2685132fb166724da46cec964f9c922701c4ae6211a5c9ee17
+size 139191256

joiner_jit_trace-pnnx.ncnn.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6dc86722065c4fcf7d6fd49750da297b36178705e6594a8aefb8a01ac0bdd655
+size 955536

joiner_jit_trace-pnnx.ncnn.param

@@ -0,0 +1,9 @@
+7767517
+7 7
+Input                    in0                      0 1 in0
+Input                    in1                      0 1 in1
+InnerProduct             linear_2                 1 1 in1 2 0=512 1=1 2=262144
+InnerProduct             linear_1                 1 1 in0 3 0=512 1=1 2=196608
+BinaryOp                 add_0                    2 1 3 2 4 0=0
+TanH                     tanh_0                   1 1 4 5
+InnerProduct             linear_3                 1 1 5 out0 0=33 1=1 2=16896

tokens.txt

@@ -0,0 +1,34 @@
+<eps> 0
+ɡ 1
+o 2
+d 3
+ʃ 4
+v 5
+t 6
+<UNK> 7
+x 8
+r 9
+ʔ 10
+b 11
+s 12
+p 13
+i 14
+dʒ 15
+| 16
+ə 17
+z 18
+f 19
+n 20
+m 21
+ɲ 22
+tʃ 23
+ŋ 24
+k 25
+j 26
+l 27
+h 28
+w 29
+a 30
+u 31
+e 32
+#0 33