e2k 0.2.2__tar.gz → 0.2.3__tar.gz

{e2k-0.2.2/src/e2k.egg-info → e2k-0.2.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: e2k
-Version: 0.2.2
+Version: 0.2.3
 Summary: A tool for automatic English to Katakana conversion
 Author-email: Patchethium <asguftuikh@gmail.com>
 Requires-Python: >=3.10
@@ -37,14 +37,25 @@ p2k = P2K()
 
 g2p = G2p()
 
-katakana = p2k(g2p("word"))
+word = "word"
+
+word = word.lower()
+
+# you can check the accepted symbols using
+in_table = c2k.in_table # `c2k` accepts lowercase characters, space and apostrophe
+in_table = p2k.in_table # `p2k` accepts the phonemes from the CMUdict and space
+# for output symbols
+out_table = c2k.out_table
+out_table = p2k.out_table
+
+katakana = p2k(g2p(word))
 
 print(katakana) # "ワード"
 
-# character directly to katakana
+# characters directly to katakana
 c2k = C2K()
 
-katakana = c2k("word")
+katakana = c2k(word)
 
 print(katakana) # "ワード"
 
@@ -58,6 +69,9 @@ c2k.set_decode_strategy("top_p", top_p=0.6, t=0.8)
 print(katakana) # "ワード"
 ```
 
+> [!WARNING]
+> For any symbols not in the `in_table`, the model will ignore them and may produce unexpected results.
+
 ### Performance
 
 The BLEU score is calculated on a random subset with size of 10% of the dataset.
@@ -164,10 +178,10 @@ The model should be exported to `numpy` format for production use.
 
 ```bash
 # --p2k for phoneme to katakana, if not provided, it will be character to katakana
-# --fp16 for half precision, there's no reason not to use it
+# --fp32 for double precision, by default we use fp16 to save space
 # --output to specify the output file, in this project it's `model-{p2k/c2k}.npz`
 # --safetenors to use safe tensors, it's for easier binding in some languages
-python export.py --model /path/to/your/model.pth --p2k --fp16 --output /path/to/your/model.npz
+python export.py --model /path/to/your/model.pth --p2k --output /path/to/your/model.npz
 ```
 
 > [!Note]

{e2k-0.2.2 → e2k-0.2.3}/README.md

@@ -28,14 +28,25 @@ p2k = P2K()
 
 g2p = G2p()
 
-katakana = p2k(g2p("word"))
+word = "word"
+
+word = word.lower()
+
+# you can check the accepted symbols using
+in_table = c2k.in_table # `c2k` accepts lowercase characters, space and apostrophe
+in_table = p2k.in_table # `p2k` accepts the phonemes from the CMUdict and space
+# for output symbols
+out_table = c2k.out_table
+out_table = p2k.out_table
+
+katakana = p2k(g2p(word))
 
 print(katakana) # "ワード"
 
-# character directly to katakana
+# characters directly to katakana
 c2k = C2K()
 
-katakana = c2k("word")
+katakana = c2k(word)
 
 print(katakana) # "ワード"
 
@@ -49,6 +60,9 @@ c2k.set_decode_strategy("top_p", top_p=0.6, t=0.8)
 print(katakana) # "ワード"
 ```
 
+> [!WARNING]
+> For any symbols not in the `in_table`, the model will ignore them and may produce unexpected results.
+
 ### Performance
 
 The BLEU score is calculated on a random subset with size of 10% of the dataset.
@@ -155,10 +169,10 @@ The model should be exported to `numpy` format for production use.
 
 ```bash
 # --p2k for phoneme to katakana, if not provided, it will be character to katakana
-# --fp16 for half precision, there's no reason not to use it
+# --fp32 for double precision, by default we use fp16 to save space
 # --output to specify the output file, in this project it's `model-{p2k/c2k}.npz`
 # --safetenors to use safe tensors, it's for easier binding in some languages
-python export.py --model /path/to/your/model.pth --p2k --fp16 --output /path/to/your/model.npz
+python export.py --model /path/to/your/model.pth --p2k --output /path/to/your/model.npz
 ```
 
 > [!Note]

{e2k-0.2.2 → e2k-0.2.3}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "e2k"
-version = "0.2.2"
+version = "0.2.3"
 description = "A tool for automatic English to Katakana conversion"
 readme = "README.md"
 authors = [{ name = "Patchethium", email = "asguftuikh@gmail.com" }]

{e2k-0.2.2 → e2k-0.2.3/src/e2k.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: e2k
-Version: 0.2.2
+Version: 0.2.3
 Summary: A tool for automatic English to Katakana conversion
 Author-email: Patchethium <asguftuikh@gmail.com>
 Requires-Python: >=3.10
@@ -37,14 +37,25 @@ p2k = P2K()
 
 g2p = G2p()
 
-katakana = p2k(g2p("word"))
+word = "word"
+
+word = word.lower()
+
+# you can check the accepted symbols using
+in_table = c2k.in_table # `c2k` accepts lowercase characters, space and apostrophe
+in_table = p2k.in_table # `p2k` accepts the phonemes from the CMUdict and space
+# for output symbols
+out_table = c2k.out_table
+out_table = p2k.out_table
+
+katakana = p2k(g2p(word))
 
 print(katakana) # "ワード"
 
-# character directly to katakana
+# characters directly to katakana
 c2k = C2K()
 
-katakana = c2k("word")
+katakana = c2k(word)
 
 print(katakana) # "ワード"
 
@@ -58,6 +69,9 @@ c2k.set_decode_strategy("top_p", top_p=0.6, t=0.8)
 print(katakana) # "ワード"
 ```
 
+> [!WARNING]
+> For any symbols not in the `in_table`, the model will ignore them and may produce unexpected results.
+
 ### Performance
 
 The BLEU score is calculated on a random subset with size of 10% of the dataset.
@@ -164,10 +178,10 @@ The model should be exported to `numpy` format for production use.
 
 ```bash
 # --p2k for phoneme to katakana, if not provided, it will be character to katakana
-# --fp16 for half precision, there's no reason not to use it
+# --fp32 for double precision, by default we use fp16 to save space
 # --output to specify the output file, in this project it's `model-{p2k/c2k}.npz`
 # --safetenors to use safe tensors, it's for easier binding in some languages
-python export.py --model /path/to/your/model.pth --p2k --fp16 --output /path/to/your/model.npz
+python export.py --model /path/to/your/model.pth --p2k --output /path/to/your/model.npz
 ```
 
 > [!Note]