GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
Panga-Azazia
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
Panga-Azazia
Model Tree
Panga-Azazia/Wuro-Mali-Tanle-v0
Input Modalities
Output Modalities
Supported Functionality
This model was developed for speech synthesis in 17 African languages.
It uses an autoregressive approach that combines tokenized text with audio codecs.
bm)bmq)dyu)dts)myk)ffm)bbo)thq)mos)kao)spp)sep)sev)dyi)mwk)wol)taq)en)fr)This model is a extended version of Panga-Azazia/Wuro-Mali-Tanle.
The model was finetuned on dataset built from Bible and galsenai/anta_women_tts .
bash
pip install unsloth snacpip install git+https://github.com/sudoping01/bambara-text-normalization.gitpython
from unsloth import FastLanguageModelimport torch model, tokenizer = FastLanguageModel.from_pretrained( model_name="Panga-Azazia/Wuro-Nucobiyo-Tanle", max_seq_length=4096, dtype=None, load_in_4bit=False,) FastLanguageModel.for_inference(model)python
tokenizer = AutoTokenizer.from_pretrained("Panga-Azazia/Wuro-Nucobiyo-Tanle", trust_remote_code=True)model = AutoModelForCausalLM.from_pretrained( "Panga-Azazia/Wuro-Nucobiyo-Tanle", trust_remote_code=True)The bambara_normalizer module is used only for Bambara. It is used to normalize certain parts of the text before generation.
For more information on how to use it, see: bambara-text-normalizer
python
import torchfrom snac import SNACimport soundfile as sfimport numpy as npfrom unsloth import FastLanguageModelfrom bambara_normalizer import normalize_dates_in_text, normalize_measurements_in_text, normalize_numbers_in_text, normalize_times_in_text CODE_START_TOKEN_ID = 128257CODE_END_TOKEN_ID = 128258CODE_TOKEN_OFFSET = 128266SNAC_MIN_ID = 128266SNAC_MAX_ID = 156937SNAC_TOKENS_PER_FRAME = 7 SOH_ID = 128259EOH_ID = 128260SOA_ID = 128261BOS_ID = 128000TEXT_EOT_ID = 128009 tokeniser_length = 128256pad_token = tokeniser_length + 7 # -------------------------------------------------------------------------------------------------------------# Normalizer from sudoping01 : see https://github.com/sudoping01/bambara-text-normalization.git for more info;# --------------------------------------------------------------------------------------------------------------def normalize_text(text: str) -> str: """Normalize text.""" text = normalize_dates_in_text(text) text = normalize_times_in_text(text) text = normalize_measurements_in_text(text) text = normalize_numbers_in_text(text) return text def build_prompt(tokenizer, lang: str, text: str) -> str: soh_token = tokenizer.decode([SOH_ID]) eoh_token = tokenizer.decode([EOH_ID]) soa_token = tokenizer.decode([SOA_ID]) sos_token = tokenizer.decode([CODE_START_TOKEN_ID]) eot_token = tokenizer.decode([TEXT_EOT_ID]) bos_token = tokenizer.bos_token if lang.lower() == "bambara" : text = normalize_text(text) formatted_text = f"<description=Read the following text in {lang}> {text}" prompt = ( soh_token + bos_token + formatted_text + eot_token + eoh_token + soa_token + sos_token ) return prompt def extract_snac_codes(token_ids: list) -> list: try: eos_idx = token_ids.index(CODE_END_TOKEN_ID) except ValueError: eos_idx = len(token_ids) return [ token_id for token_id in token_ids[:eos_idx] if SNAC_MIN_ID <= token_id <= SNAC_MAX_ID ] def unpack_snac_from_7(snac_tokens: list) -> list: """Unpack 7-token SNAC frames to 3 hierarchical levels.""" if snac_tokens and snac_tokens[-1] == CODE_END_TOKEN_ID: snac_tokens = snac_tokens[:-1] frames = len(snac_tokens) // SNAC_TOKENS_PER_FRAME snac_tokens = snac_tokens[:frames * SNAC_TOKENS_PER_FRAME] if frames == 0: return [[], [], []] l1, l2, l3 = [], [], [] for i in range(frames): slots = snac_tokens[i * 7:(i + 1) * 7] l1.append((slots[0] - CODE_TOKEN_OFFSET) % 4096) l2.extend([ (slots[1] - CODE_TOKEN_OFFSET) % 4096, (slots[4] - CODE_TOKEN_OFFSET) % 4096, ]) l3.extend([ (slots[2] - CODE_TOKEN_OFFSET) % 4096, (slots[3] - CODE_TOKEN_OFFSET) % 4096, (slots[5] - CODE_TOKEN_OFFSET) % 4096, (slots[6] - CODE_TOKEN_OFFSET) % 4096, ]) return [l1, l2, l3] snac_model = SNAC.from_pretrained("hubertsiuzdak/snac_24khz").eval() def main(lang = "Bomu", text = "bwe wa wuro." , temp = .4, top_p = .9, max_tokens = 2048, min_tokens = 28, rp = 1.2): if lang not in ["Bambara", "Bomu", "Dogon", "Minianka"] : lang = lang.lower() prompt = build_prompt(tokenizer, lang, text) inputs = tokenizer(prompt, return_tensors="pt", add_special_tokens=True) if torch.cuda.is_available(): inputs = {k: v.to("cuda") for k, v in inputs.items()} with torch.inference_mode(): outputs = model.generate( **inputs, max_new_tokens=max_tokens, min_new_tokens=min_tokens, temperature=temp, top_p=top_p, repetition_penalty=rp, do_sample=True, eos_token_id=CODE_END_TOKEN_ID, pad_token_id=tokenizer.pad_token_id, ) generated_ids = outputs[0, inputs['input_ids'].shape[1]:].tolist() if CODE_END_TOKEN_ID in generated_ids: eos_position = generated_ids.index(CODE_END_TOKEN_ID) print(f" EOS token found at position {eos_position}/{len(generated_ids)}") snac_tokens = extract_snac_codes(generated_ids) print(f"Extracted {len(snac_tokens)} SNAC tokens") snac_count = sum(1 for t in generated_ids if SNAC_MIN_ID <= t <= SNAC_MAX_ID) other_count = sum(1 for t in generated_ids if t < SNAC_MIN_ID or t > SNAC_MAX_ID) print(f" SNAC tokens in output: {snac_count}") print(f" Other tokens in output: {other_count}") # Check for SOS token if CODE_START_TOKEN_ID in generated_ids: sos_pos = generated_ids.index(CODE_START_TOKEN_ID) print(f" SOS token at position: {sos_pos}") else: print(f" No SOS token found in generated output!") if len(snac_tokens) < 7: print("Error: Not enough SNAC tokens generated") return # Unpack SNAC tokens to 3 hierarchical levels levels = unpack_snac_from_7(snac_tokens) frames = len(levels[0]) print(f"Unpacked to {frames} frames") print(f" L1: {len(levels[0])} codes") print(f" L2: {len(levels[1])} codes") print(f" L3: {len(levels[2])} codes") device = "cuda" if torch.cuda.is_available() else "cpu" codes_tensor = [ torch.tensor(level, dtype=torch.long, device=device).unsqueeze(0) for level in levels ] with torch.inference_mode(): z_q = snac_model.quantizer.from_codes(codes_tensor) audio = snac_model.decoder(z_q)[0, 0].cpu().numpy() # Trim warmup samples (first 2048 samples) if len(audio) > max_tokens: audio = audio[max_tokens:] duration_sec = len(audio) / 24000 print(f"Audio generated: {len(audio)} samples ({duration_sec:.2f}s)") output_file = f"{lang}-{text}.wav" sf.write(output_file, audio, 24000)A Bomu audio sample.
python
main( lang = "Bomu", text="Ho lana a sinciri cinnu, ho a ziya berobe nɛ zeni be nɛ mi, a nucoro yire ɓɛɛ da mi.")A Fulfulde audio sample.
python
main( lang = "fulfulde", text = "Goonɗinal yo taƴorde heɓan ko fawi jikke e mum e hoolaade ko yiyaali ana woodi." )A Wolof audio sample.
python
main( lang = "wolof", text= "iniwersite bu ndar, ëmb na juróorum-ñaari bërëbu tàggat ak gëstu.", )A Bambara audio sample.
python
main( lang = "Bambara", text="Ayiwa, an jigi bɛ fɛn minnu kan, dannaya ye olu jɛyali ye. Dannaya bɛ fɛn yebaliw seereya kɛ." )A Konabere audio sample.
python
main( lang = "konabere", text="Laɩnapɩ tɩɛɛ n’ɩ kɔ nʋ: ŋma daŋ ma ma tɩgɛɩmapɩ ti, ŋmɔ na jisigefaa, ŋma fɩrɛɛ ma m’ɩ jaa ko, ŋmɔ na sɩɛrɩpɩ.", )A Khassonke audio sample.
python
main( lang = "khassonke", text="Lannaya mu ɲin ne ti xo: Í gigo be fenŋo men xan, wo soto be xoyiyanin í ma; walla í ɲa nte fenŋo men na, í b'a yitanin xo í ɲa be wo la.", )A English audio sample.
python
main( lang = "english", text="Now faith is the substance of things hoped for, the evidence of things not seen.", )A Songhay-timbuktu audio sample.
python
main( lang = "songhay-timbuktu", text="Naanay ci, ka kow sika hayadiyo ra ka ni go tammaha, nda ka tabatindi hayadiyo ka ni si guna.", )A Moore audio sample.
python
main( lang = "moore", text="Wẽnd sẽn pʋlem tõnd vʋʋsgã, tɩ b kãabga ket n yɛsẽ wã, d maan dabeem, tɩ yãmb nin-yend na n wa yet tɩ b basa yẽ kɛɛnga.", )A French audio sample.
python
main( lang = "french", text="Or la foi est une ferme assurance des choses qu’on espère, une démonstration de celles qu’on ne voit pas.", )A Fulfulde audio sample.
python
main( lang = "fulfulde", text = "Goonɗinal yo taƴorde heɓan ko fawi jikke e mum e hoolaade ko yiyaali ana woodi." )A Dogon audio sample.
python
main( lang = "Dogon", text="Kijɛ emɛ dɔmɔ bɛbɛɛdɛin ga diyɛ daanu ye bii gɔ, gagawu gɔ woi. Gagawu, kijɛ iyemɔɔlɛ gɔbe yɔɔin ga diyɛ daanu ye bii.", )A Minianka audio sample.
python
main( lang = "Minianka", text="Ayiwa, nʼa daa wʼa wèe wo tadaŋa ki wo yaŋmuyɔ yi keree fiinŋɛ, na wèe pye wèe ya tiin ni li ni na yi wa wèe mu na xɔ. Nʼa daa wʼa wèe pye wèe ya sɔɔ li na na can wa yaŋmuɲabaaya yi wo keree ki ni.", )A jula audio sample.
python
main( lang = "jula", text="Lanaya ye min ye, o ye nin ye i be la fɛɛn dɔ la, k'i jigi la a kan k'a sɔrɔ i m'a ye ka ye. Fɔlɔfɔlɔ mɔgɔw ye tɔgɔɲuman sɔrɔ Ala fɛ u ka lanaya kosɔn.", )A Senoufo-Djimini audio sample.
python
main( lang = "Senoufo-Djimini", text="Na we kaga jɛn mbe yo we jigi wi yɛn yaraga ŋga na we yaa ki ta, ko ki yɛn tagawa we. Tagawa po pi yɛn yaraga ŋga we woro na yaan, we taga ki na we yo ki yɛn kaselege.", )A Senoufo-Shempire audio sample.
python
main( lang = "Senoufo-Shempire ", text="Ɲaha ku ɲyɛ dániyaŋi yɛ? Mà ma sɔ̀nŋɔre taha yaaga na maa ntɛ̀ɛn ná l'e mu sí ku ta, lire ɲyɛ mɛ yaage ku ɲyɛ mu ɲyɛ na ku ɲaa mɛ, maa dá ku na mu à jwo mu ɲyii na ɲyɛ ku na ke, lire li ɲyɛ dániyaŋi.", )A Senoufo-Nyarafolo audio sample.
python
main( lang = "Senoufo-Nyarafolo", text="Tɛ́ngɛlɛ ni kɔri wire yē bè tɛ́ngɛ ki nɛ̄ gìi nɛ̄ muɔ nyɛ́nì muɔ sɔ̀ngirɔ taʔa dè, muɔ bé ki taa, bè ki cɛ́n gàa muɔ wè nɛ nyaʔa gèʔ, kiī kányiʔɛ.", )A Malinke audio sample.
python
main( lang = "malinke", text="Lannaya dun ye le xo ilan jigi ye hɛn mɛnnu xan, olu jusigilan ne ye, ilan ɲa ye ntɛ hɛn mɛnnu la, olu seeriyali le ye.", )A tamasheq audio sample.
python
main( lang = "tamasheq", text="Immun, ălmăɣna-net a-s a-wa dăɣ-ijăr ăwadəm ăṭṭăma, ad-has-umas šund a-s insa data-s; meɣ daɣ, a-wa-dăɣ wăr-ihənnəy s-tiṭṭawen-net, ad-has-umas šund ăsiḍălalăk dăɣ-s." )You can also use one language's voice to read text written in another.
A English audio sample. Here the model are reading English using Wolof accent.
python
main( lang = "wolof", text="Now faith is the substance of things hoped for, the evidence of things not seen.", )We are noticed some misalignment on Moore dataset, so the speech generated could probably not reflect the given Text.
The french speech is not yet at the point the model struggle to generate clear speech in it.
| Name | Description | Notebook |
|---|---|---|
| SFT (Unsloth) | Supervised Fine-Tuning with LoRA using Unsloth. |
The Wolof dataset used is from galsenai/anta_women_tts.
text
@dataset{galsenai_anta, author = {GalsenAI-Lab}, abstract = {Anta is a cleaned version of the Baamtu Wolof TTS dataset. We extracted the female voice, denoised it and enhanced it with the Resemble Enhance library. We also cleaned up the annotations by removing special characters, emojis, Arabic and Russian characters. We've corrected a few annotation errors, but there are potentially many more to come. Some lines and audios judged not qualitative enough have been removed from the dataset, reducing its size to 19947 annotated audios.}, title = {Anta: Wolof female-voice Text-to-Speech dataset}, howpublished = {\url{https://huggingface.co/datasets/galsenai/anta_women_tts}}, year = {2024}}pip install unsloth snacpip install git+https://github.com/sudoping01/bambara-text-normalization.gitfrom unsloth import FastLanguageModelimport torch model, tokenizer = FastLanguageModel.from_pretrained( model_name="Panga-Azazia/Wuro-Nucobiyo-Tanle", max_seq_length=4096, dtype=None, load_in_4bit=False,) FastLanguageModel.for_inference(model)tokenizer = AutoTokenizer.from_pretrained("Panga-Azazia/Wuro-Nucobiyo-Tanle", trust_remote_code=True)model = AutoModelForCausalLM.from_pretrained( "Panga-Azazia/Wuro-Nucobiyo-Tanle", trust_remote_code=True)import torchfrom snac import SNACimport soundfile as sfimport numpy as npfrom unsloth import FastLanguageModelfrom bambara_normalizer import normalize_dates_in_text, normalize_measurements_in_text, normalize_numbers_in_text, normalize_times_in_text CODE_START_TOKEN_ID = 128257CODE_END_TOKEN_ID = 128258CODE_TOKEN_OFFSET = 128266SNAC_MIN_ID = 128266SNAC_MAX_ID = 156937SNAC_TOKENS_PER_FRAME = 7 SOH_ID = 128259EOH_ID = 128260SOA_ID = 128261BOS_ID = 128000TEXT_EOT_ID = 128009 tokeniser_length = 128256pad_token = tokeniser_length + 7 # -------------------------------------------------------------------------------------------------------------# Normalizer from sudoping01 : see https://github.com/sudoping01/bambara-text-normalization.git for more info;# --------------------------------------------------------------------------------------------------------------def normalize_text(text: str) -> str: """Normalize text.""" text = normalize_dates_in_text(text) text = normalize_times_in_text(text) text = normalize_measurements_in_text(text) text = normalize_numbers_in_text(text) return text def build_prompt(tokenizer, lang: str, text: str) -> str: soh_token = tokenizer.decode([SOH_ID]) eoh_token = tokenizer.decode([EOH_ID]) soa_token = tokenizer.decode([SOA_ID]) sos_token = tokenizer.decode([CODE_START_TOKEN_ID]) eot_token = tokenizer.decode([TEXT_EOT_ID]) bos_token = tokenizer.bos_token if lang.lower() == "bambara" : text = normalize_text(text) formatted_text = f"<description=Read the following text in {lang}> {text}" prompt = ( soh_token + bos_token + formatted_text + eot_token + eoh_token + soa_token + sos_token ) return prompt def extract_snac_codes(token_ids: list) -> list: try: eos_idx = token_ids.index(CODE_END_TOKEN_ID) except ValueError: eos_idx = len(token_ids) return [ token_id for token_id in token_ids[:eos_idx] if SNAC_MIN_ID <= token_id <= SNAC_MAX_ID ] def unpack_snac_from_7(snac_tokens: list) -> list: """Unpack 7-token SNAC frames to 3 hierarchical levels.""" if snac_tokens and snac_tokens[-1] == CODE_END_TOKEN_ID: snac_tokens = snac_tokens[:-1] frames = len(snac_tokens) // SNAC_TOKENS_PER_FRAME snac_tokens = snac_tokens[:frames * SNAC_TOKENS_PER_FRAME] if frames == 0: return [[], [], []] l1, l2, l3 = [], [], [] for i in range(frames): slots = snac_tokens[i * 7:(i + 1) * 7] l1.append((slots[0] - CODE_TOKEN_OFFSET) % 4096) l2.extend([ (slots[1] - CODE_TOKEN_OFFSET) % 4096, (slots[4] - CODE_TOKEN_OFFSET) % 4096, ]) l3.extend([ (slots[2] - CODE_TOKEN_OFFSET) % 4096, (slots[3] - CODE_TOKEN_OFFSET) % 4096, (slots[5] - CODE_TOKEN_OFFSET) % 4096, (slots[6] - CODE_TOKEN_OFFSET) % 4096, ]) return [l1, l2, l3] snac_model = SNAC.from_pretrained("hubertsiuzdak/snac_24khz").eval() def main(lang = "Bomu", text = "bwe wa wuro." , temp = .4, top_p = .9, max_tokens = 2048, min_tokens = 28, rp = 1.2): if lang not in ["Bambara", "Bomu", "Dogon", "Minianka"] : lang = lang.lower() prompt = build_prompt(tokenizer, lang, text) inputs = tokenizer(prompt, return_tensors="pt", add_special_tokens=True) if torch.cuda.is_available(): inputs = {k: v.to("cuda") for k, v in inputs.items()} with torch.inference_mode(): outputs = model.generate( **inputs, max_new_tokens=max_tokens, min_new_tokens=min_tokens, temperature=temp, top_p=top_p, repetition_penalty=rp, do_sample=True, eos_token_id=CODE_END_TOKEN_ID, pad_token_id=tokenizer.pad_token_id, ) generated_ids = outputs[0, inputs['input_ids'].shape[1]:].tolist() if CODE_END_TOKEN_ID in generated_ids: eos_position = generated_ids.index(CODE_END_TOKEN_ID) print(f" EOS token found at position {eos_position}/{len(generated_ids)}") snac_tokens = extract_snac_codes(generated_ids) print(f"Extracted {len(snac_tokens)} SNAC tokens") snac_count = sum(1 for t in generated_ids if SNAC_MIN_ID <= t <= SNAC_MAX_ID) other_count = sum(1 for t in generated_ids if t < SNAC_MIN_ID or t > SNAC_MAX_ID) print(f" SNAC tokens in output: {snac_count}") print(f" Other tokens in output: {other_count}") # Check for SOS token if CODE_START_TOKEN_ID in generated_ids: sos_pos = generated_ids.index(CODE_START_TOKEN_ID) print(f" SOS token at position: {sos_pos}") else: print(f" No SOS token found in generated output!") if len(snac_tokens) < 7: print("Error: Not enough SNAC tokens generated") return # Unpack SNAC tokens to 3 hierarchical levels levels = unpack_snac_from_7(snac_tokens) frames = len(levels[0]) print(f"Unpacked to {frames} frames") print(f" L1: {len(levels[0])} codes") print(f" L2: {len(levels[1])} codes") print(f" L3: {len(levels[2])} codes") device = "cuda" if torch.cuda.is_available() else "cpu" codes_tensor = [ torch.tensor(level, dtype=torch.long, device=device).unsqueeze(0) for level in levels ] with torch.inference_mode(): z_q = snac_model.quantizer.from_codes(codes_tensor) audio = snac_model.decoder(z_q)[0, 0].cpu().numpy() # Trim warmup samples (first 2048 samples) if len(audio) > max_tokens: audio = audio[max_tokens:] duration_sec = len(audio) / 24000 print(f"Audio generated: {len(audio)} samples ({duration_sec:.2f}s)") output_file = f"{lang}-{text}.wav" sf.write(output_file, audio, 24000)main( lang = "Bomu", text="Ho lana a sinciri cinnu, ho a ziya berobe nɛ zeni be nɛ mi, a nucoro yire ɓɛɛ da mi.")main( lang = "fulfulde", text = "Goonɗinal yo taƴorde heɓan ko fawi jikke e mum e hoolaade ko yiyaali ana woodi." )main( lang = "wolof", text= "iniwersite bu ndar, ëmb na juróorum-ñaari bërëbu tàggat ak gëstu.", )main( lang = "Bambara", text="Ayiwa, an jigi bɛ fɛn minnu kan, dannaya ye olu jɛyali ye. Dannaya bɛ fɛn yebaliw seereya kɛ." )main( lang = "konabere", text="Laɩnapɩ tɩɛɛ n’ɩ kɔ nʋ: ŋma daŋ ma ma tɩgɛɩmapɩ ti, ŋmɔ na jisigefaa, ŋma fɩrɛɛ ma m’ɩ jaa ko, ŋmɔ na sɩɛrɩpɩ.", )main( lang = "khassonke", text="Lannaya mu ɲin ne ti xo: Í gigo be fenŋo men xan, wo soto be xoyiyanin í ma; walla í ɲa nte fenŋo men na, í b'a yitanin xo í ɲa be wo la.", )main( lang = "english", text="Now faith is the substance of things hoped for, the evidence of things not seen.", )main( lang = "songhay-timbuktu", text="Naanay ci, ka kow sika hayadiyo ra ka ni go tammaha, nda ka tabatindi hayadiyo ka ni si guna.", )main( lang = "moore", text="Wẽnd sẽn pʋlem tõnd vʋʋsgã, tɩ b kãabga ket n yɛsẽ wã, d maan dabeem, tɩ yãmb nin-yend na n wa yet tɩ b basa yẽ kɛɛnga.", )main( lang = "french", text="Or la foi est une ferme assurance des choses qu’on espère, une démonstration de celles qu’on ne voit pas.", )main( lang = "fulfulde", text = "Goonɗinal yo taƴorde heɓan ko fawi jikke e mum e hoolaade ko yiyaali ana woodi." )main( lang = "Dogon", text="Kijɛ emɛ dɔmɔ bɛbɛɛdɛin ga diyɛ daanu ye bii gɔ, gagawu gɔ woi. Gagawu, kijɛ iyemɔɔlɛ gɔbe yɔɔin ga diyɛ daanu ye bii.", )main( lang = "Minianka", text="Ayiwa, nʼa daa wʼa wèe wo tadaŋa ki wo yaŋmuyɔ yi keree fiinŋɛ, na wèe pye wèe ya tiin ni li ni na yi wa wèe mu na xɔ. Nʼa daa wʼa wèe pye wèe ya sɔɔ li na na can wa yaŋmuɲabaaya yi wo keree ki ni.", )main( lang = "jula", text="Lanaya ye min ye, o ye nin ye i be la fɛɛn dɔ la, k'i jigi la a kan k'a sɔrɔ i m'a ye ka ye. Fɔlɔfɔlɔ mɔgɔw ye tɔgɔɲuman sɔrɔ Ala fɛ u ka lanaya kosɔn.", )main( lang = "Senoufo-Djimini", text="Na we kaga jɛn mbe yo we jigi wi yɛn yaraga ŋga na we yaa ki ta, ko ki yɛn tagawa we. Tagawa po pi yɛn yaraga ŋga we woro na yaan, we taga ki na we yo ki yɛn kaselege.", )main( lang = "Senoufo-Shempire ", text="Ɲaha ku ɲyɛ dániyaŋi yɛ? Mà ma sɔ̀nŋɔre taha yaaga na maa ntɛ̀ɛn ná l'e mu sí ku ta, lire ɲyɛ mɛ yaage ku ɲyɛ mu ɲyɛ na ku ɲaa mɛ, maa dá ku na mu à jwo mu ɲyii na ɲyɛ ku na ke, lire li ɲyɛ dániyaŋi.", )main( lang = "Senoufo-Nyarafolo", text="Tɛ́ngɛlɛ ni kɔri wire yē bè tɛ́ngɛ ki nɛ̄ gìi nɛ̄ muɔ nyɛ́nì muɔ sɔ̀ngirɔ taʔa dè, muɔ bé ki taa, bè ki cɛ́n gàa muɔ wè nɛ nyaʔa gèʔ, kiī kányiʔɛ.", )main( lang = "malinke", text="Lannaya dun ye le xo ilan jigi ye hɛn mɛnnu xan, olu jusigilan ne ye, ilan ɲa ye ntɛ hɛn mɛnnu la, olu seeriyali le ye.", )main( lang = "tamasheq", text="Immun, ălmăɣna-net a-s a-wa dăɣ-ijăr ăwadəm ăṭṭăma, ad-has-umas šund a-s insa data-s; meɣ daɣ, a-wa-dăɣ wăr-ihənnəy s-tiṭṭawen-net, ad-has-umas šund ăsiḍălalăk dăɣ-s." )main( lang = "wolof", text="Now faith is the substance of things hoped for, the evidence of things not seen.", )@dataset{galsenai_anta, author = {GalsenAI-Lab}, abstract = {Anta is a cleaned version of the Baamtu Wolof TTS dataset. We extracted the female voice, denoised it and enhanced it with the Resemble Enhance library. We also cleaned up the annotations by removing special characters, emojis, Arabic and Russian characters. We've corrected a few annotation errors, but there are potentially many more to come. Some lines and audios judged not qualitative enough have been removed from the dataset, reducing its size to 19947 annotated audios.}, title = {Anta: Wolof female-voice Text-to-Speech dataset}, howpublished = {\url{https://huggingface.co/datasets/galsenai/anta_women_tts}}, year = {2024}}