初始化项目，由ModelHub XC社区提供模型

Model: saheedniyi/YarnGPT-local
Source: Original Platform

.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
+audio/YarnGPT-Local.mp4 filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,403 @@
+---
+library_name: transformers
+language:
+- yo
+- ig
+- ha
+base_model:
+- HuggingFaceTB/SmolLM2-360M
+- saheedniyi/YarnGPT
+pipeline_tag: text-to-speech
+license: cc-by-nc-sa-4.0
+---
+
+# YarnGPT-local
+![image/png](https://huggingface.co/saheedniyi/YarnGPT/resolve/main/audio/logo.webp)
+
+## Table of Contents
+
+1. [Model Summary](#model-summary)  
+2. [Model Description](#model-description)  
+3. [Bias, Risks, and Limitations](#bias-risks-and-limitations)  
+   - [Recommendations](#recommendations)  
+4. [Speech Samples](#speech-samples)  
+5. [Training](#training)  
+6. [Future Improvements](#future-improvements)  
+7. [Citation](#citation)  
+8. [Credits & References](#credits--references)
+
+## Model Summary
+
+YarnGPT-local is a text-to-speech (TTS) model designed to synthesize Yoruba, Igbo and Hausa leveraging pure language modelling without external adapters or complex architectures, offering high-quality, natural, and culturally relevant speech synthesis for diverse applications.
+
+<video controls width="600">
+  <source src="https://huggingface.co/saheedniyi/YarnGPT-local/resolve/main/audio/YarnGPT-Local.mp4" type="video/mp4">
+  Your browser does not support the video tag.
+</video>
+
+#### How to use (on Google Colab)
+The model can generate audio on its own but its better to use a voice to prompt the model, there are about 10 voices supported by default:
+- hausa_female1
+- hausa_female2
+- hausa_male1
+- hausa_male2
+- igbo_female1
+- igbo_female2
+- igbo_male2
+- yoruba_female1
+- yoruba_female2
+- yoruba_male2
+
+### Prompt YarnGPT-local
+```python
+# clone the YarnGPT repo to get access to the `audiotokenizer`
+!git clone https://github.com/saheedniyi02/yarngpt.git
+
+
+# install some necessary libraries
+!pip install outetts==0.2.3 uroman
+
+#import some important packages 
+import os
+import re
+import json
+import torch
+import inflect
+import random
+import uroman as ur
+import numpy as np
+import torchaudio
+import IPython
+from transformers import AutoModelForCausalLM, AutoTokenizer
+from outetts.wav_tokenizer.decoder import WavTokenizer
+from yarngpt.audiotokenizer import AudioTokenizerForLocal
+
+
+# download the wavtokenizer weights and config (to encode and decode the audio)
+!wget https://huggingface.co/novateur/WavTokenizer-medium-speech-75token/resolve/main/wavtokenizer_mediumdata_frame75_3s_nq1_code4096_dim512_kmeans200_attn.yaml
+!gdown 1-ASeEkrn4HY49yZWHTASgfGFNXdVnLTt
+
+# model path and wavtokenizer weight path (the paths are assumed based on Google colab, a different environment might save the weights to a different location).
+hf_path="saheedniyi/YarnGPT-local"
+wav_tokenizer_config_path="/content/wavtokenizer_mediumdata_frame75_3s_nq1_code4096_dim512_kmeans200_attn.yaml"
+wav_tokenizer_model_path = "/content/wavtokenizer_large_speech_320_24k.ckpt"
+
+# create the AudioTokenizer object 
+audio_tokenizer=AudioTokenizerForLocal(
+    hf_path,wav_tokenizer_model_path,wav_tokenizer_config_path
+)
+
+#load the model weights
+
+model = AutoModelForCausalLM.from_pretrained(hf_path,torch_dtype="auto").to(audio_tokenizer.device)
+
+# your input text
+text="Ẹ maa rii pe lati bi ọsẹ meloo kan ni ijiroro ti wa lati ọdọ awọn ileeṣẹ wọnyi wi pe wọn fẹẹ ṣafikun si owo ipe pẹlu ida ọgọrun-un."
+
+# creating a prompt, when creating a prompt, there is an optional `speaker_name` parameter
+prompt=audio_tokenizer.create_prompt(text,"yoruba","yoruba_male2")
+
+# tokenize the prompt
+input_ids=audio_tokenizer.tokenize_prompt(prompt)
+
+# generate output from the model, you can tune the `.generate` parameters as you wish
+output  = model.generate(
+            input_ids=input_ids,
+            temperature=0.1,
+            repetition_penalty=1.1,
+            num_beams=4,
+            max_length=4000,
+        )
+
+# convert the output to "audio codes"
+codes=audio_tokenizer.get_codes(output)
+
+# converts the codes to audio 
+audio=audio_tokenizer.get_audio(codes)
+
+# play the audio
+IPython.display.Audio(audio,rate=24000)
+
+# save the audio 
+torchaudio.save(f"audio.wav", audio, sample_rate=24000)
+```
+
+### Simple News-Reader for Local languages
+```python
+# clone the YarnGPT repo to get access to the `audiotokenizer`
+!git clone https://github.com/saheedniyi02/yarngpt.git
+
+
+# install some necessary libraries
+!pip install outetts uroman trafilatura pydub
+
+
+#import important packages
+import os
+import re
+import json
+import torch
+import inflect
+import random
+import requests
+import trafilatura
+import inflect
+import uroman as ur
+import numpy as np
+import torchaudio
+import IPython
+from pydub import AudioSegment
+from pydub.effects import normalize
+from transformers import AutoModelForCausalLM, AutoTokenizer
+from outetts.wav_tokenizer.decoder import WavTokenizer
+from yarngpt.audiotokenizer import AudioTokenizer,AudioTokenizerForLocal
+
+# download the `WavTokenizer` files
+!wget https://huggingface.co/novateur/WavTokenizer-medium-speech-75token/resolve/main/wavtokenizer_mediumdata_frame75_3s_nq1_code4096_dim512_kmeans200_attn.yaml
+!gdown 1-ASeEkrn4HY49yZWHTASgfGFNXdVnLTt
+
+tokenizer_path="saheedniyi/YarnGPT-local"
+wav_tokenizer_config_path="/content/wavtokenizer_mediumdata_frame75_3s_nq1_code4096_dim512_kmeans200_attn.yaml"
+wav_tokenizer_model_path = "/content/wavtokenizer_large_speech_320_24k.ckpt"
+
+
+audio_tokenizer=AudioTokenizerForLocal(
+    tokenizer_path,wav_tokenizer_model_path,wav_tokenizer_config_path
+       )
+
+model = AutoModelForCausalLM.from_pretrained(tokenizer_path,torch_dtype="auto").to(audio_tokenizer.device)
+
+# Split text into chunks
+def split_text_into_chunks(text, word_limit=25):
+  sentences=[sentence.strip() for sentence in text.split('.') if sentence.strip()]
+  chunks=[]
+  for sentence in sentences:
+    chunks.append(".")
+    sentence_splitted=sentence.split(" ")
+    num_words=len(sentence_splitted)
+    start_index=0
+    if num_words>word_limit:
+      while start_index<num_words:
+        end_index=min(num_words,start_index+word_limit)
+        chunks.append(" ".join(sentence_splitted[start_index:start_index+word_limit]))
+        start_index=end_index
+    else:
+      chunks.append(sentence)
+  return chunks
+
+# reduce the speed of the audio, results from the local languages are always fast
+def speed_change(sound, speed=0.9):
+    # Manually override the frame_rate. This tells the computer how many
+    # samples to play per second
+    sound_with_altered_frame_rate = sound._spawn(sound.raw_data, overrides={
+         "frame_rate": int(sound.frame_rate * speed)
+      })
+     # convert the sound with altered frame rate to a standard frame rate
+     # so that regular playback programs will work right. They often only
+     # know how to play audio at standard frame rate (like 44.1k)
+    return sound_with_altered_frame_rate.set_frame_rate(sound.frame_rate)
+
+
+page=requests.get("https://alaroye.org/a-maa-too-fo-ipinle-ogun-mo-omo-egbe-okunkun-meje-lowo-ti-te-bayii-omolola/")
+content=trafilatura.extract(page.text)
+chunks=split_text_into_chunks(content)
+
+
+all_codes=[]
+for i,chunk in enumerate(chunks):
+  print(i)
+  print("\n")
+  print(chunk)
+  if chunk==".":
+    #add silence for 0.5 seconds if we encounter a full stop
+    all_codes.extend([453]*38)
+  else:
+    prompt=audio_tokenizer.create_prompt(chunk,lang="yoruba",speaker_name="yoruba_female2")
+    input_ids=audio_tokenizer.tokenize_prompt(prompt)
+    output  = model.generate(
+            input_ids=input_ids,
+            temperature=0.1,
+            repetition_penalty=1.1,
+            max_length=4000,
+            num_beams=5,
+        )
+    codes=audio_tokenizer.get_codes(output)
+    all_codes.extend(codes)
+
+
+audio=audio_tokenizer.get_audio(all_codes)
+
+#display the output
+IPython.display.Audio(audio,rate=24000)
+
+#save audio
+torchaudio.save(f"news1.wav", audio, sample_rate=24000)
+
+#convert file to an `AudioSegment` object for furher processing
+audio_dub=AudioSegment.from_file("news1.wav")
+
+# reduce audio speed: it reduces quality also
+speed_change(audio_dub,0.9)
+```
+
+
+## Model Description
+
+- **Developed by:** [Saheedniyi](https://linkedin.com/in/azeez-saheed)
+- **Model type:** Text-to-Speech
+- **Language(s) (NLP):** Igbo, Yoruba, Hausa--> Speech
+- **Finetuned from:** [HuggingFaceTB/SmolLM2-360M](https://huggingface.co/HuggingFaceTB/SmolLM2-360M)
+- **Repository:** [YarnGPT Github Repository](https://github.com/saheedniyi02/yarngpt)
+- **Paper:** IN PROGRESS.
+- **Demo:** 1) [Prompt YarnGPT-local notebook](https://colab.research.google.com/drive/1UWeirECQbjFGib1SqpiDdkzS1Bi_vi9i?usp=sharing)
+            2) [Simple news reader: YarnGPT-local](https://colab.research.google.com/drive/1CMsLVsDaX2u4YUtV01fOvnDCtCC59bNe?usp=sharing)
+
+#### Uses
+
+Generate yoruba, igbo and hausa speech for experimental purposes.
+
+
+#### Out-of-Scope Use
+
+The model is not suitable for generating speech in languages other than Yoruba, Igbo and Hausa.
+
+
+## Bias, Risks, and Limitations
+
+- The model may not capture the full diversity of Nigerian accents and could exhibit biases based on the training dataset.
+- The audio generated by the model are sometimes very fast and might need some post-processing to be done.
+- The model doesn't take 'intonations' into account which sometimes leads to mispronounce meant of some words.
+- Model doesn't respond to some prompt
+
+
+
+#### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases, and limitations of the model. Feedback and diverse training data contributions are encouraged.
+## Speech Samples
+
+Listen to samples generated by YarnGPT:
+
+<div style="margin-top: 20px;">
+<table style="width: 100%; border-collapse: collapse;">
+  <thead>
+    <tr>
+        <th style="border: 1px solid #ddd; padding: 8px; text-align: left; width: 40%;">Input</th>
+        <th style="border: 1px solid #ddd; padding: 8px; text-align: left; width: 40%;">Audio</th>
+        <th style="border: 1px solid #ddd; padding: 8px; text-align: left; width: 10%;">Notes</th>
+    </tr>
+  </thead>
+  <tbody>
+    <tr>
+        <td style="border: 1px solid #ddd; padding: 8px;">Ẹ maa rii pe lati bi ọsẹ meloo kan ni ijiroro ti wa lati ọdọ awọn ileeṣẹ wọnyi wi pe wọn fẹẹ ṣafikun si owo ipe pẹlu ida ọgọrun-un</td>
+        <td style="border: 1px solid #ddd; padding: 8px;">
+            <audio controls style="width: 100%;">
+                <source src="https://huggingface.co/saheedniyi/YarnGPT-local/resolve/main/audio/Sample1_yor.wav" type="audio/wav">
+                Your browser does not support the audio element.
+            </audio>
+        </td>
+        <td style="border: 1px solid #ddd; padding: 8px;">(temperature=0.1, repetition_penalty=1.1,num_beams=4), voice: yoruba_male2</td>
+    </tr>
+    <tr>
+        <td style="border: 1px solid #ddd; padding: 8px;"> Iwadii fihan pe ọkan lara awọn eeyan meji yii lo ṣee si ja sinu tanki epo disu naa lasiko to n ṣiṣẹ lọwọ.</td>
+        <td style="border: 1px solid #ddd; padding: 8px;">
+            <audio controls style="width: 100%;">
+                <source src="https://huggingface.co/saheedniyi/YarnGPT-local/resolve/main/audio/Sample2_yor.wav" type="audio/wav">
+                Your browser does not support the audio element.
+            </audio>
+        </td>
+        <td style="border: 1px solid #ddd; padding: 8px;">(temperature=0.1, repetition_penalty=1.1,num_beams=4), voice: yoruba_female1</td>
+    </tr>
+    <tr>
+        <td style="border: 1px solid #ddd; padding: 8px;"> Shirun da gwamnati mai ci yanzu ta yi wajen kin bayani a akan halin da ake ciki a game da batun kidayar shi ne ya janyo wannan zargi da jam'iyyar ta Labour ta yi.</td>
+        <td style="border: 1px solid #ddd; padding: 8px;">
+            <audio controls style="width: 100%;">
+                <source src="https://huggingface.co/saheedniyi/YarnGPT-local/resolve/main/audio/Sample1_hau.wav" type="audio/wav">
+                Your browser does not support the audio element.
+            </audio>
+        </td>
+        <td style="border: 1px solid #ddd; padding: 8px;">(temperature=0.1, repetition_penalty=1.1,num_beams=4), voice: hausa_male2</td>
+    </tr>
+    <tr>
+        <td style="border: 1px solid #ddd; padding: 8px;">A lokuta da dama yakan fito a matsayin jarumin da ke taimaka wa babban jarumi, kodayake a wasu fina-finan yakan fito a matsayin babban jarumi.</td>
+        <td style="border: 1px solid #ddd; padding: 8px;">
+            <audio controls style="width: 100%;">
+                <source src="https://huggingface.co/saheedniyi/YarnGPT-local/resolve/main/audio/Sample2_hau.wav" type="audio/wav">
+                Your browser does not support the audio element.
+            </audio>
+        </td>
+        <td style="border: 1px solid #ddd; padding: 8px;">(temperature=0.1, repetition_penalty=1.1,num_beams=4), voice: hausa_female1</td>
+    </tr>
+    <tr>
+        <td style="border: 1px solid #ddd; padding: 8px;">Amụma ndị ọzọ o buru gụnyere inweta ihe zuru oke, ịmụta ụmụaka nye ndị na-achọ nwa</td>
+        <td style="border: 1px solid #ddd; padding: 8px;">
+            <audio controls style="width: 100%;">
+                <source src="https://huggingface.co/saheedniyi/YarnGPT-local/resolve/main/audio/Sample1_igb.wav" type="audio/wav">
+                Your browser does not support the audio element.
+            </audio>
+        </td>
+        <td style="border: 1px solid #ddd; padding: 8px;">(temperature=0.1, repetition_penalty=1.1,num_beams=4), voice: igbo_female1</td>
+    </tr>
+  </tbody>
+  </table>
+</div>
+
+
+## Training
+
+#### Data
+Trained on open source dataset on Yoruba, Igbo and Hausa.
+
+#### Preprocessing 
+
+Audio files were preprocessed and resampled to 24Khz and tokenized using [wavtokenizer](https://huggingface.co/novateur/WavTokenizer).
+
+#### Training Hyperparameters
+- **Number of epochs:** 5
+- **batch_size:** 4
+- **Scheduler:** linear schedule with warmup for 4 epochs, then linear decay to zero for the last epoch
+- **Optimizer:** AdamW (betas=(0.9, 0.95),weight_decay=0.01)
+- **Learning rate:** 1*10^-3
+
+#### Hardware
+
+- **GPUs:** 1 A100 (google colab: 30 hours)
+
+#### Software
+
+- **Training Framework:** Pytorch
+
+## Future Improvements?
+- Scaling up model size and training data
+- Wrap the model around an API endpoint 
+- Voice cloning.
+- Potential expansion into speech-to-speech assistant models
+
+## Citation [optional]
+
+#### BibTeX:
+
+```python
+@misc{yarngpt2025,
+  author = {Saheed Azeez},
+  title = {YarnGPT: Nigerian-Accented English Text-to-Speech Model},
+  year = {2025},
+  publisher = {Hugging Face},
+  url = {https://huggingface.co/SaheedAzeez/yarngpt}
+}
+```
+
+#### APA:
+
+```python
+Saheed Azeez. (2025). YarnGPT-local: Nigerian languages Text-to-Speech Model. Hugging Face. Available at: https://huggingface.co/saheedniyi/YarnGPT-local
+```
+
+
+## Credits & References
+- [OuteAI/OuteTTS-0.2-500M](https://huggingface.co/OuteAI/OuteTTS-0.2-500M/)
+- [WavTokenizer](https://github.com/jishengpeng/WavTokenizer)
+- [CTC Forced Alignment](https://pytorch.org/audio/stable/tutorials/ctc_forced_alignment_api_tutorial.html)
+- [Voicera](https://huggingface.co/Lwasinam/voicera)

audio/YarnGPT-Local.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b4fdd6811b48195d578a108ff7b4e74075027d0e97b26a9e8453fb6d217c618
+size 10598161

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "saheedniyi/yih2",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 960,
+  "initializer_range": 0.02,
+  "intermediate_size": 2560,
+  "is_llama_config": true,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 15,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 5,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_interleaved": false,
+  "rope_scaling": null,
+  "rope_theta": 100000,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.47.1",
+  "use_cache": true,
+  "vocab_size": 53248
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "transformers_version": "4.47.1"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e0b051e69263daa6d1d56d3ec6eab95900535142f61745008a70b9a1ffddeea
+size 731539240

special_tokens_map.json

@@ -0,0 +1,49 @@
+{
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "<|im_start|>",
+    "<|im_end|>",
+    "<repo_name>",
+    "<reponame>",
+    "<file_sep>",
+    "<filename>",
+    "<gh_stars>",
+    "<issue_start>",
+    "<issue_comment>",
+    "<issue_closed>",
+    "<jupyter_start>",
+    "<jupyter_text>",
+    "<jupyter_code>",
+    "<jupyter_output>",
+    "<jupyter_script>",
+    "<empty_output>"
+  ],
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}